Detailed Action
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Amendment filed on 01/28/2026 has been acknowledged. Claims 1-12, 14-18 and 20, as originally filed, are currently pending and have been considered below. Claim 1, 14 and 20 are independent claim. Claim 13 and 19 are cancelled.
Priority
No priority claimed.
Remarks and Response
Applicant’s arguments filed in the amendments on 01/28/2026 have been fully considered but moot in view of new ground of rejection. The reasons set forth below.
Regarding claim 1: On pages 7-8 of the arguments filed on 01/28/2026, applicant argued that cited reference does not teach the newly amended limitation in claim 1: “add the serving cell ID to a blacklist”. Examiner agreed and introduced new reference Koral to teach the limitation.
Regarding claim 14: On pages 8-9 of the arguments filed on 01/28/2026, applicant argued that cited reference Pathania and Briggs do not teach the limitation of claim 19 that has been included in claim 14. There is no mention of neighboring cell in [0044].
Examiner respectfully disagrees. Pathania, ¶[0044], the data stored in database may be retrieved by the security management system and used to develop and validate the model. ¶[0080], the machine learning models employ machine learning algorithm such as nearest neighbor (NN) algorithm. ¶[0082], the K-Nearest neighbors algorithm may receive each data point within the signal characteristic data and compare each to k closest data points
Regarding claim 20: On pages 9-10 of the arguments filed on 01/28/2026, applicant argued that claim 20 has been amended to include recitation of claim 11. Ensemble machine learning model is not taught by the cited reference that uses two or more of those three models as recited in claim.
Examiner respectfully disagrees. Pathania, ¶[0045], the feature engineering module can generate device specific models for each user device based on the historical signal characteristics data between the user device with a known legitimate cell site. The device specific models can enhance anomaly detection. ¶[0046], most appropriate model for detection and determination of anomaly. ¶[0076]- ¶[0077], machine learning classifier learns to differentiate. ¶[0080], machine learning models employ machine learning algorithms such as nearest neighbor algorithm, statistical algorithm, replicating reservoir networks (for non-linear models typically for time series)
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim 1-12 are rejected under 35 U.S.C. 103 as being unpatentable over Pathania (US Patent Application No 2025/0119748 A1) in view of Briggs (US Patent No 10,129,283 B1) and further in view of Koral (US Patent Application Publication No 2023/0308878 A1).
Regarding Claim 1, Pathania discloses a computer-implemented method comprising:
obtaining, by one or more processors, radio frequency (RF) signal scan data indicative of RF conditions in a cell of an operator base station (Pathania, ¶[0032], receiver is responsible for capturing and processing incoming wireless signals from cell sites such as legitimate cell site or cell site simulator. ¶[0034], the signal measurement component is responsible for measuring the signals transmitted between the user device and a cell site. ¶[0035], the signal characteristics data includes cell site identifier, timestamp data, signal information block (SIB), signal strength data, signal to noise ratio data, signal frequency data, error rate data (bit error and packet error), signal bandwidth data, carrier to interference ratio, geolocation data);
inputting, by the one or more processors, the RF signal scan data into a machine learning model trained at least in part using historical RF signal scan data indicative of base station operation in an absence of a rogue base station (Pathania, ¶[0020], the method leverage historical signal characteristics data obtained from signal transmissions between user devices and known legitimate cell sites to construct a model aimed at distinguishing legitimate from suspicious cell sites. ¶[0043], the model may include the determined acceptable range and the algorithms used for feature engineering. The model includes machine learning models. ¶[0045], the feature engineering module can generate device specific models for each user device, based on the historical signal characteristics data between the user device with a known legitimate cell site);
detecting, by the one or more processors, an output of the machine learning model indicative of a presence of a rogue base station (Pathania, ¶[0048], based on the outcome of comparison of the actual features against the expected features and the determination of the actual clusters against the acceptable range, the determination module can further determine whether the cell site is a suspicious cell site. ¶[0049], the verification application is responsible to confirm the legitimacy of the suspicious cell. ¶[0051], the protection application initiates an immediate disconnection of the user device from cell site simulator); and
generating, by the one or more processors, an alert indicative of the presence of the rogue base station (Pathania, ¶[0036], providing visual or auditory alerts to inform users about changes in network conditions, signal characteristics and the detection of suspicious signal characteristics and allowing the user to provide feedback or report issues related to signal characteristics. ¶[0051], user may be notified of the detected anomaly, threat of the cell simulator and the protective action is taken).
determining, by the one or more processors, a serving cell ID associated with the rogue base station (Pathania, ¶[0019], analyzing signal characteristics beyond cell ID and frequency. These characteristics may encompass parameters like signal strength, signal to noise ratio, interference levels. ¶[0035], signal characteristics data include cell ID, timestamp, signal information block (SIB) data, signal strength data, signal to noise ratio data, signal frequency data, bit error rate, packet error rate, signal bandwidth data (the width of the frequency spectrum occupied by the signal in a specific period of time), signal latency data, carrier to interference ratio data, geolocation data); and
transmitting, by the one or more processors, the serving cell ID to user equipment and refrains from attaching to one or more base stations associated with the serving cell ID (Pathania, ¶[0098], a protective action is taken by the user device to cause a disconnection from the suspicious cell site. Data transmission between the user device and the suspicious cell site is ceased).
Pathania does not explicitly teach the following limitation that Briggs teaches:
rogue base station (Briggs, col 3, line 50-60, a rogue base station may directly interfere with a UE’s serving cell. Fig-1. Col 8, line 30-40).
Pathania in view of Briggs are analogous art because they are from the “same field of endeavor” and are from the same “problem solving area”. Namely, they pertain to the field of “detecting rogue base station”. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the invention of Pathania in view of Briggs to include the idea of analyzing waveforms and signaling messages from a base station and determining whether communication with the base station should be avoided (Briggs, col 1, line 5-10).
Pathania in view of Briggs do not explicitly teach the following limitation that Koral teaches:
such that the user equipment adds the serving cell ID to a blacklist (Koral, ¶[0047], the vendor and model analyzer sub-module can maintain a blacklist for vendors and models of access point that are known for being popular for attacker. In response to determining that the vendor or model is on the black list, the vendor and model analyzer sub-module can determine that the access point has a higher likelihood of being malicious).
Pathania in view of Briggs and Koral are analogous art because they are from the “same field of endeavor” and are from the same “problem solving area”. Namely, they pertain to the field of “access point impersonation protection”. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the invention of Pathania in view of Briggs and Koral to include the idea of incorporating an access point impersonation protection system that can determine whether the vendor or the model of the access point is on a blacklist (Koral, ¶[0009).
Regarding Claim 2, Pathania in view of Briggs and Koral discloses the computer-implemented method of claim 1, wherein the RF signal scan data includes indications of random access channel (RACH) failures, standalone dedicated control channel (SDDCH) failures, signal to noise ratio (SINR) values, received signal strength indicator (RSSI) values, or received total wideband power (RTWP) values generated by the operator base station (Pathania, ¶[0019], analyzing signal characteristics beyond cell ID and frequency. These characteristics may encompass parameters like signal strength, signal to noise ratio, interference levels. ¶[0035], signal characteristics data include cell ID, timestamp, signal information block (SIB) data, signal strength data, signal to noise ratio data, signal frequency data, bit error rate, packet error rate, signal bandwidth data (the width of the frequency spectrum occupied by the signal in a specific period of time), signal latency data, carrier to interference ratio data, geolocation data. Also, Briggs, Col 4, line 15-20, received signal strength indication (RSSI), col 55-60, random access channel procedure (RACH)).
Regarding Claim 3, Pathania in view of Briggs and Koral discloses the computer-implemented method of claim 1, wherein the RF signal scan data includes indications of bit error rate, block error rate, power levels at carrier frequencies, out-of-band power levels, subcarrier spacing, or channel allocation data generated by performing a frequency-domain analysis of signals received at the operator base station (Pathania, ¶[0019], analyzing signal characteristics beyond cell ID and frequency. These characteristics may encompass parameters like signal strength, signal to noise ratio, interference levels. ¶[0035], signal characteristics data include cell ID, timestamp, signal information block (SIB) data, signal strength data, signal to noise ratio data, signal frequency data, bit error rate, packet error rate, signal bandwidth data (the width of the frequency spectrum occupied by the signal in a specific period of time), signal latency data, carrier to interference ratio data, geolocation data).
Regarding Claim 4, Pathania in view of Briggs and Koral discloses the computer-implemented method of claim 1, wherein the RF signal scan data includes indications of reference signal receive power (RSRP), reference signal received quality (RSRQ), reference signal SINR (RS-SINR), serving cell RF information, neighbor cell RF information, cell ID, or serving cell ID generated by (i) user equipment (UE) served by the operator base station or (ii) a neighboring cell to the cell of the operator base station (Pathania, ¶[0019], analyzing signal characteristics beyond cell ID and frequency. These characteristics may encompass parameters like signal strength, signal to noise ratio, interference levels. ¶[0035], signal characteristics data include cell ID, timestamp, signal information block (SIB) data, signal strength data, signal to noise ratio data, signal frequency data, bit error rate, packet error rate, signal bandwidth data (the width of the frequency spectrum occupied by the signal in a specific period of time), signal latency data, carrier to interference ratio data, geolocation data. Also Briggs, col 10, line 10-15, RSSI as measures using reference signal received power (RSRP)).
Regarding Claim 5, Pathania in view of Briggs and Koral the computer-implemented method of claim 1, further comprising:
obtaining, by one or more processors, a plurality of RF signal scan data from a plurality of operator base stations (Pathania, ¶[0044], the database is in connection with security management system and may include various data sources provided by third party or public, such as geolocation data, crime statistics data and law enforcement data); and
storing, by the one or more processors, the plurality of RF signal scan data in a database (Pathania, ¶[0044], the database is in connection with security management system and may include various data sources provided by third party or public, such as geolocation data, crime statistics data and law enforcement data).
Regarding Claim 6, Pathania in view of Briggs and Koral discloses the computer-implemented method of claim 5, further comprising:
validating, by the one or more processors, the presence of the rogue base station by:
obtaining, from the database, RF signal scan data associated with a neighboring cell (Pathania, ¶[0044], the geolocation data may include geolocation of cell sites, user devices or potential anomalies which can be used for spatial analysis and geofencing. The data stored in database may be retrieved by the security management system and used to develop and validate the model); and
inputting the RF signal scan data associated with the neighboring cell into the machine learning model (Pathania, ¶[0044], the geolocation data may include geolocation of cell sites, user devices or potential anomalies which can be used for spatial analysis and geofencing. The data stored in database may be retrieved by the security management system and used to develop and validate the model).
Regarding Claim 7, Pathania in view of Briggs and Koral discloses the computer-implemented method of claim 6, wherein generating the alert comprises:
detecting, by the one or more processors, an output of the machine learning model indicative of the presence of the rogue base station when the RF signal scan data associated with the neighboring cell (Pathania, ¶[0048], based on the outcome of comparison of the actual features against the expected features and the determination of the actual clusters against the acceptable range, the determination module can further determine whether the cell site is a suspicious cell site. ¶[0049], the verification application is responsible to confirm the legitimacy of the suspicious cell. ¶[0051], the protection application initiates an immediate disconnection of the user device from cell site simulator);
estimating, by the one or more processors, a location of the rogue base station based on a coverage area associated with the cell and the neighboring cell (Pathania, ¶[0055], the geographic area where the cell site simulator located is identified based on simultaneous identification of the cell site simulator. A positioning technique such as bilateral or triangulation may be employed. The security management system compares angles measured by different user devices and identifies an intersection point where lines of sight from the user devices converge. The intersection point may represent the estimated location of the cell site simulator. ¶[0104]); and
generating, by the one or more processors, the alert such that the alert indicates the estimated location (Pathania, ¶[0051], user may be notified of the detected anomaly, threat of the cell simulator and the protective action is taken. ¶[0104], the suspicious cell site is located based on the geolocation data and position data included in the signal characteristics data associated with each user device. The location of the suspicious cell site may be reported to a third party such as law enforcement).
Regarding Claim 8, Pathania in view of Briggs and Koral discloses the computer-implemented method of claim 1, wherein:
the machine learning model is an anomaly detection model (Pathania, ¶[0045], the feature engineering module can generate device specific models for each user device based on the historical signal characteristics data between the user device with a known legitimate cell site. The device specific models can enhance anomaly detection. ¶[0046], most appropriate model for detection and determination of anomaly); and
the machine learning model is (i) trained using historical RF signal scan data generated by the operator base station to generate a baseline for operation of operator base station, and (ii) output the indication of the presence of the rogue base station in response to detecting a deviation between the obtained RF signal scan data and the baseline (Pathania, ¶[0020], the method leverages historical signal characteristics data obtained from signal transmissions between user devices and known legitimate cell sites to construct a model aimed at distinguishing legitimate from suspicious cell sites. ¶[0045]).
Regarding Claim 9, Pathania in view of Briggs and Koral discloses the computer-implemented method of claim 1, wherein:
the machine learning model is a classification model (Pathania, ¶[0045], the feature engineering module can generate device specific models for each user device based on the historical signal characteristics data between the user device with a known legitimate cell site. The device specific models can enhance anomaly detection. ¶[0046], most appropriate model for detection and determination of anomaly); and
the machine learning model is (i) trained using labeled historical RF signal scan data indicative of base station operation in an absence of a rogue base station and labeled historical RF signal scan data indicative of base station operation in a presence of a rogue base station, and (ii) output the indication of the presence of the rogue base station by classifying the RF signal scan data with a label indicative of the presence of the rogue base station (Pathania, ¶[0020], the method leverages historical signal characteristics data obtained from signal transmissions between user devices and known legitimate cell sites to construct a model aimed at distinguishing legitimate from suspicious cell sites. ¶[0045]).
Regarding Claim 10, Pathania in view of Briggs and Koral discloses the computer-implemented method of claim 1, wherein:
the machine learning model is a time series analysis model (Pathania, ¶[0045], the feature engineering module can generate device specific models for each user device based on the historical signal characteristics data between the user device with a known legitimate cell site. The device specific models can enhance anomaly detection. ¶[0046], most appropriate model for detection and determination of anomaly); and
the machine learning model is (i) trained using historical RF signal scan data indicative of base station operation over time in an absence of a rogue base station, (ii) accepts a plurality of RF signal scan data obtained from the operator base station generated across an interval of time, and (iii) output the indication of the presence of the rogue base station in response to detecting an anomalous pattern of operation (Pathania, ¶[0020], the method leverages historical signal characteristics data obtained from signal transmissions between user devices and known legitimate cell sites to construct a model aimed at distinguishing legitimate from suspicious cell sites. ¶[0045]).
Regarding Claim 11, Pathania in view of Briggs and Koral discloses the computer-implemented method of claim 1, wherein:
the machine learning model is an ensemble machine learning model that includes two or more of an anomaly detection model, a classification model, and a time series analysis model (Pathania, ¶[0045], the feature engineering module can generate device specific models for each user device based on the historical signal characteristics data between the user device with a known legitimate cell site. The device specific models can enhance anomaly detection. ¶[0046], most appropriate model for detection and determination of anomaly. ¶[0076]- ¶[0077], machine learning classifier learns to differentiate. ¶[0080], machine learning models employ machine learning algorithms such as nearest neighbor algorithm, statistical algorithm, replicating reservoir networks (for non-linear models typically for time series)).
Regarding Claim 12, Pathania in view of Briggs and Koral discloses the computer-implemented method of claim 1, wherein the operator base station captures the RF signal scan data during a period of low activity (Pathania, ¶[0032], receiver is responsible for capturing and processing incoming wireless signals from cell sites such as legitimate cell site or cell site simulator. ¶[0034], the signal measurement component is responsible for measuring the signals transmitted between the user device and a cell site. ¶[0035], the signal characteristics data includes cell site identifier, timestamp data, signal information block (SIB), signal strength data, signal to noise ratio data, signal frequency data, error rate data (bit error and packet error), signal bandwidth data, carrier to interference ratio, geolocation data).
Claim 14-18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Pathania (US Patent Application No 2025/0119748 A1) in view of Briggs (US Patent No 10,129,283 B1).
Regarding Claim 14, Pathania discloses a system comprising:
one or more transceivers communicatively coupled to an operator base station (Pathania, Fig-7);
one or more processors (Pathania, Fig-7); and
one or more non-transitory memories storing processor-executable instructions that, when executed by the one or more processors, cause the system to (Pathania, Fig-7):
obtain radio frequency (RF) signal scan data indicative of RF conditions in a cell of an operator base station (Pathania, ¶[0032], receiver is responsible for capturing and processing incoming wireless signals from cell sites such as legitimate cell site or cell site simulator. ¶[0034], the signal measurement component is responsible for measuring the signals transmitted between the user device and a cell site. ¶[0035], the signal characteristics data includes cell site identifier, timestamp data, signal information block (SIB), signal strength data, signal to noise ratio data, signal frequency data, error rate data (bit error and packet error), signal bandwidth data, carrier to interference ratio, geolocation data);
input the RF signal scan data into a machine learning model trained at least in part using historical RF signal scan data indicative of base station operation in an absence of a rogue base station (Pathania, ¶[0020], the method leverage historical signal characteristics data obtained from signal transmissions between user devices and known legitimate cell sites to construct a model aimed at distinguishing legitimate from suspicious cell sites. ¶[0043], the model may include the determined acceptable range and the algorithms used for feature engineering. The model includes machine learning models. ¶[0045], the feature engineering module can generate device specific models for each user device, based on the historical signal characteristics data between the user device with a known legitimate cell site);
detect an output of the machine learning model indicative of a presence of a rogue base station (Pathania, ¶[0048], based on the outcome of comparison of the actual features against the expected features and the determination of the actual clusters against the acceptable range, the determination module can further determine whether the cell site is a suspicious cell site. ¶[0049], the verification application is responsible to confirm the legitimacy of the suspicious cell. ¶[0051], the protection application initiates an immediate disconnection of the user device from cell site simulator); and
generate an alert indicative of the presence of the rogue base station (Pathania, ¶[0036], providing visual or auditory alerts to inform users about changes in network conditions, signal characteristics and the detection of suspicious signal characteristics and allowing the user to provide feedback or report issues related to signal characteristics. ¶[0051], user may be notified of the detected anomaly, threat of the cell simulator and the protective action is taken).
validate the presence of the rogue base station by:
obtaining, from a database, RF signal scan data associated with a neighboring cell (Pathania, ¶[0044], the geolocation data may include geolocation of cell sites, user devices or potential anomalies which can be used for spatial analysis and geofencing. The data stored in database may be retrieved by the security management system and used to develop and validate the model); and
inputting the RF signal scan data associated with the neighboring cell into the machine learning model (Pathania, ¶[0044], the geolocation data may include geolocation of cell sites, user devices or potential anomalies which can be used for spatial analysis and geofencing. The data stored in database may be retrieved by the security management system and used to develop and validate the model. ¶[0080], the machine learning models employ machine learning algorithm such as nearest neighbor (NN) algorithm. ¶[0082], the K-Nearest neighbors algorithm may receive each data point within the signal characteristic data and compare each to k closest data points).
Pathania does not explicitly teach the following limitation that Briggs teaches:
rogue base station (Briggs, col 3, line 50-60, a rogue base station may directly interfere with a UE’s serving cell. Fig-1. Col 8, line 30-40).
Pathania in view of Briggs are analogous art because they are from the “same field of endeavor” and are from the same “problem solving area”. Namely, they pertain to the field of “detecting rogue base station”. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the invention of Pathania in view of Briggs to include the idea of analyzing waveforms and signaling messages from a base station and determining whether communication with the base station should be avoided (Briggs, col 1, line 5-10).
Regarding Claim 15, Pathania in view of Briggs discloses the system of claim 14, wherein:
the machine learning model is an anomaly detection model (Pathania, ¶[0045], the feature engineering module can generate device specific models for each user device based on the historical signal characteristics data between the user device with a known legitimate cell site. The device specific models can enhance anomaly detection. ¶[0046], most appropriate model for detection and determination of anomaly); and
the machine learning model is (i) trained using historical RF signal scan data generated by the operator base station to generate a baseline for operation of operator base station, and (ii) output the indication of the presence of the rogue base station in response to detecting a deviation between the obtained RF signal scan data and the baseline (Pathania, ¶[0020], the method leverages historical signal characteristics data obtained from signal transmissions between user devices and known legitimate cell sites to construct a model aimed at distinguishing legitimate from suspicious cell sites. ¶[0045]).
Regarding Claim 16, Pathania in view of Briggs discloses the system of claim 14, wherein:
the machine learning model is a classification model (Pathania, ¶[0045], the feature engineering module can generate device specific models for each user device based on the historical signal characteristics data between the user device with a known legitimate cell site. The device specific models can enhance anomaly detection. ¶[0046], most appropriate model for detection and determination of anomaly); and
the machine learning model is (i) trained using labeled historical RF signal scan data indicative of base station operation in an absence of a rogue base station and labeled historical RF signal scan data indicative of base station operation in a presence of a rogue base station, and (ii) output the indication of the presence of the rogue base station by classifying the RF signal scan data with a label indicative of the presence of the rogue base station (Pathania, ¶[0020], the method leverages historical signal characteristics data obtained from signal transmissions between user devices and known legitimate cell sites to construct a model aimed at distinguishing legitimate from suspicious cell sites. ¶[0045]).
Regarding Claim 17, Pathania in view of Briggs discloses the system of claim 14, wherein:
the machine learning model is a time series analysis model (Pathania, ¶[0045], the feature engineering module can generate device specific models for each user device based on the historical signal characteristics data between the user device with a known legitimate cell site. The device specific models can enhance anomaly detection. ¶[0046], most appropriate model for detection and determination of anomaly); and
the machine learning model is (i) trained using historical RF signal scan data indicative of base station operation over time in an absence of a rogue base station, (ii) accepts a plurality of RF signal scan data obtained from the operator base station generated across an interval of time, and (iii) output the indication of the presence of the rogue base station in response to detecting an anomalous pattern of operation (Pathania, ¶[0020], the method leverages historical signal characteristics data obtained from signal transmissions between user devices and known legitimate cell sites to construct a model aimed at distinguishing legitimate from suspicious cell sites. ¶[0045]).
Regarding Claim 18, Pathania in view of Briggs discloses the system of claim 14, wherein:
the machine learning model is an ensemble machine learning model that includes two or more of an anomaly detection model, a classification model, and a time series analysis model (Pathania, ¶[0045], the feature engineering module can generate device specific models for each user device based on the historical signal characteristics data between the user device with a known legitimate cell site. The device specific models can enhance anomaly detection. ¶[0046], most appropriate model for detection and determination of anomaly. ¶[0076]- ¶[0077], machine learning classifier learns to differentiate. ¶[0080], machine learning models employ machine learning algorithms such as nearest neighbor algorithm, statistical algorithm, replicating reservoir networks (for non-linear models typically for time series)).
Regarding Claim 20, Pathania discloses a non-transitory storage medium storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to:
obtain radio frequency (RF) signal scan data indicative of RF conditions in a cell of an operator base station (Pathania, ¶[0032], receiver is responsible for capturing and processing incoming wireless signals from cell sites such as legitimate cell site or cell site simulator. ¶[0034], the signal measurement component is responsible for measuring the signals transmitted between the user device and a cell site. ¶[0035], the signal characteristics data includes cell site identifier, timestamp data, signal information block (SIB), signal strength data, signal to noise ratio data, signal frequency data, error rate data (bit error and packet error), signal bandwidth data, carrier to interference ratio, geolocation data);
input the RF signal scan data into a machine learning model trained at least in part using historical RF signal scan data indicative of base station operation in an absence of a rogue base station (Pathania, ¶[0020], the method leverage historical signal characteristics data obtained from signal transmissions between user devices and known legitimate cell sites to construct a model aimed at distinguishing legitimate from suspicious cell sites. ¶[0043], the model may include the determined acceptable range and the algorithms used for feature engineering. The model includes machine learning models. ¶[0045], the feature engineering module can generate device specific models for each user device, based on the historical signal characteristics data between the user device with a known legitimate cell site);
detect an output of the machine learning model indicative of a presence of a rogue base station (Pathania, ¶[0048], based on the outcome of comparison of the actual features against the expected features and the determination of the actual clusters against the acceptable range, the determination module can further determine whether the cell site is a suspicious cell site. ¶[0049], the verification application is responsible to confirm the legitimacy of the suspicious cell. ¶[0051], the protection application initiates an immediate disconnection of the user device from cell site simulator); and
generate an alert indicative of the presence of the rogue base station (Pathania, ¶[0036], providing visual or auditory alerts to inform users about changes in network conditions, signal characteristics and the detection of suspicious signal characteristics and allowing the user to provide feedback or report issues related to signal characteristics. ¶[0051], user may be notified of the detected anomaly, threat of the cell simulator and the protective action is taken);
wherein the machine learning model is an ensemble machine learning model that includes two or more of an anomaly detection model, a classification model, and a time series analysis model (Pathania, ¶[0045], the feature engineering module can generate device specific models for each user device based on the historical signal characteristics data between the user device with a known legitimate cell site. The device specific models can enhance anomaly detection. ¶[0046], most appropriate model for detection and determination of anomaly. ¶[0076]- ¶[0077], machine learning classifier learns to differentiate. ¶[0080], machine learning models employ machine learning algorithms such as nearest neighbor algorithm, statistical algorithm, replicating reservoir networks (for non-linear models typically for time series)).
Pathania does not explicitly teach the following limitation that Briggs teaches:
rogue base station (Briggs, col 3, line 50-60, a rogue base station may directly interfere with a UE’s serving cell. Fig-1. Col 8, line 30-40).
Pathania in view of Briggs are analogous art because they are from the “same field of endeavor” and are from the same “problem solving area”. Namely, they pertain to the field of “detecting rogue base station”. It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the invention of Pathania in view of Briggs to include the idea of analyzing waveforms and signaling messages from a base station and determining whether communication with the base station should be avoided (Briggs, col 1, line 5-10).
Conclusion
Applicant’s amendment necessitated the new ground(s) of rejection presented in this office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action. Any inquiry concerning this communication or earlier communications from the examiner should be directed to WASIKA NIPA whose telephone number is (571)272-8923. The examiner can normally be reached on M-F (7:30 - 5:00).
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, JEFFRY PWU can be reached on 571-272-6798. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/WASIKA NIPA/ Primary Examiner, Art Unit 2433
Prosecution Insights