Abstract: Embodiments of the disclosure disclose a system to mitigate against adversarial input samples for machine learning (ML)/artificial intelligence (AI) models. According to one embodiment, a system receives a query from a client for a ML service. The system calculates a similarity score for the query based on a number of prior queries received from the client, the similarity score representing a similarity between the received query and the prior queries. The system determines that the query is an adversarial query in response to determining that the similarity score is above a predetermined threshold.

Abstract: In one embodiment, a system receives a first image captured by a capturing device of an ADV. The system applies an image transformation to the first image to generate a second image. The system applies an object detection model to the first and the second images to generate a first and a second output, respectively. The system calculates a similarity metric between the first and the second output. The system detects the first image as an adversarial sample if a temporal variation of the similarity metric between the first image and a prior image is above a threshold.

Abstract: In one embodiment, a system receives a first image captured by a capturing device of an ADV. The system applies an image transformation to the first image to generate a second image. The system applies an object detection model to the first and the second images to generate a first and a second output, respectively. The system calculates a similarity metric between the first and the second output. The system detects the first image as an adversarial sample if a temporal variation of the similarity metric between the first image and a prior image is above a threshold.

Abstract: Embodiments of the disclosure disclose a system to mitigate against adversarial input samples for machine learning (ML)/artificial intelligence (AI) models. According to one embodiment, a system receives a query from a client for a ML service. The system calculates a similarity score for the query based on a number of prior queries received from the client, the similarity score representing a similarity between the received query and the prior queries. The system determines that the query is an adversarial query in response to determining that the similarity score is above a predetermined threshold.

Abstract: Techniques are disclosed for determining whether a mobile device is located indoors or outdoors. In some embodiments, a mobile device may utilize a fusion of the information from multiple sensors, such as a RGB sensor, a proximity sensor, a light intensity sensor, and a WiFi radio, to determine whether the mobile device is located indoors or outdoors.

Abstract: Described herein is a network device configured to determine and provide alerts of communication link failures across layers of a communication stack of the network device. The network device determines at a radio link layer of the communication stack that a communication link between the network device and a network has failed. The network device then alerts one or more components associated with another layer of the communication stack of the determination that the communication link has failed.

Abstract: A VoLTE diagnostic engine may receive VoLTE call records of VoLTE calls that are carried by a wireless carrier network for multiple user devices. The VoLTE call records may include performance indicators and call features for the voice calls. Each call feature of a VoLTE call may represent a circumstance under which the VoLTE call is established and ended. The VoLTE diagnostic engine may apply a decision tree to the VoLTE call records to identify critical features of one or more call conditions that lead to Quality of Experience (QoE) problems for the VoLTE calls captured in the VoLTE call records. Each call condition may include a subset of the call features. Further, the VoLTE diagnostic engine may apply a classifier on the critical features to determine a root cause of a QoE problem for at least one call conditions.

Abstract: Techniques and devices for circumventing wireless data monitoring in communications between a communication device and a proxy server, as well as systems and techniques for detecting and resolving vulnerabilities in wireless data monitoring systems are described herein. The techniques for circumventing wireless data monitoring may include manipulating a routing table of a communication device, encapsulating data in an unmonitored protocol, and transmitting the encapsulated data in a “bearer,” or communications channel, to a proxy server that fulfills requests included in the encapsulated data. Furthermore, the techniques for detecting and resolving network vulnerabilities may include restricting protocols by bearers in an Access Control List, limiting a bandwidth of a bearer, or protecting a routing table in a secure location of the communication device.

Abstract: A VoLTE diagnostic engine may receive VoLTE call records of VoLTE calls that are carried by a wireless carrier network for multiple user devices. The VoLTE call records may include performance indicators and call features for the voice calls. Each call feature of a VoLTE call may represent a circumstance under which the VoLTE call is established and ended. The VoLTE diagnostic engine may apply a decision tree to the VoLTE call records to identify critical features of one or more call conditions that lead to Quality of Experience (QoE) problems for the VoLTE calls captured in the VoLTE call records. Each call condition may include a subset of the call features. Further, the VoLTE diagnostic engine may apply a classifier on the critical features to determine a root cause of a QoE problem for at least one call conditions.

Abstract: Techniques and devices for circumventing wireless data monitoring in communications between a communication device and a proxy server, as well as systems and techniques for detecting and resolving vulnerabilities in wireless data monitoring systems are described herein. The techniques for circumventing wireless data monitoring may include manipulating a routing table of a communication device, encapsulating data in an unmonitored protocol, and transmitting the encapsulated data in a “bearer,” or communications channel, to a proxy server that fulfills requests included in the encapsulated data. Furthermore, the techniques for detecting and resolving network vulnerabilities may include restricting protocols by bearers in an Access Control List, limiting a bandwidth of a bearer, or protecting a routing table in a secure location of the communication device.

Abstract: Described herein is a network device configured to determine and provide alerts of communication link failures across layers of a communication stack of the network device. The network device determines at a radio link layer of the communication stack that a communication link between the network device and a network has failed. The network device then alerts one or more components associated with another layer of the communication stack of the determination that the communication link has failed.

Abstract: Techniques are disclosed for determining whether a mobile device is located indoors or outdoors. In some embodiments, a mobile device may utilize a fusion of the information from multiple sensors, such as a RGB sensor, a proximity sensor, a light intensity sensor, and a WiFi radio, to determine whether the mobile device is located indoors or outdoors.

Abstract: A telecommunication carrier may use data collected from user devices to pinpoint sources of data interruptions in the communication connection between a carrier network and the user devices. The telecommunication carrier may receive multiple reports of detected data interruptions at one or more computing devices of a carrier network. The detected data interruptions include a data interruption to a user device that is detected by an agent application on the user device that monitors of at least one of an audio pathway or a video pathway of the user device. The telecommunication carrier may aggregate data interruption information from the multiple reports of the detected data interruptions, and analyze the data interruption information to pinpoint one or more sources of a detected data interruption.

Abstract: Described herein is a network device configured to determine and provide alerts of communication link failures across layers of a communication stack of the network device. The network device determines at a radio link layer of the communication stack that a communication link between the network device and a network has failed. The network device then alerts one or more components associated with another layer of the communication stack of the determination that the communication link has failed.

Abstract: Techniques and devices for circumventing wireless data monitoring in communications between a communication device and a proxy server, as well as systems and techniques for detecting and resolving vulnerabilities in wireless data monitoring systems are described herein. The techniques for circumventing wireless data monitoring may include manipulating a routing table of a communication device, encapsulating data in an unmonitored protocol, and transmitting the encapsulated data in a “bearer,” or communications channel, to a proxy server that fulfills requests included in the encapsulated data. Furthermore, the techniques for detecting and resolving network vulnerabilities may include restricting protocols by bearers in an Access Control List, limiting a bandwidth of a bearer, or protecting a routing table in a secure location of the communication device.

Abstract: Techniques and devices for circumventing wireless data monitoring in communications between a communication device and a proxy server, as well as systems and techniques for detecting and resolving vulnerabilities in wireless data monitoring systems are described herein. The techniques for circumventing wireless data monitoring may include manipulating a routing table of a communication device, encapsulating data in an unmonitored protocol, and transmitting the encapsulated data in a “bearer,” or communications channel, to a proxy server that fulfills requests included in the encapsulated data. Furthermore, the techniques for detecting and resolving network vulnerabilities may include restricting protocols by bearers in an Access Control List, limiting a bandwidth of a bearer, or protecting a routing table in a secure location of the communication device.

Abstract: A telecommunication carrier may use data collected from user devices to pinpoint sources of data interruptions in the communication connection between a carrier network and the user devices. The telecommunication carrier may receive multiple reports of detected data interruptions at one or more computing devices of a carrier network. The detected data interruptions include a data interruption to a user device that is detected by an agent application on the user device that monitors of at least one of an audio pathway or a video pathway of the user device. The telecommunication carrier may aggregate data interruption information from the multiple reports of the detected data interruptions, and analyze the data interruption information to pinpoint one or more sources of a detected data interruption.

Abstract: Described herein is a network device configured to determine and provide alerts of communication link failures across layers of a communication stack of the network device. The network device determines at a radio link layer of the communication stack that a communication link between the network device and a network has failed. The network device then alerts one or more components associated with another layer of the communication stack of the determination that the communication link has failed.