SIP Protocol security & Uncover its security vulnerabilities and exploit them to devise four SMS attacks: silent SMS abuse, SMS spoofing, SMS client DoS, and SMS spamming
Text embedding from the General Purpose Language Model captures a lot of sensitive information from plain text, which can be reverse-engineered to disclose sensitive information about the victim for further harassment.
SISA training, a framework designed to achieve the largest improvements for stateful algorithms like stochastic gradient descent for deep neural networks, reduces the computational overhead associated with unlearning.
We present a novel mobile/IoT device identification and abnormal device detection mechanism named OWL. OWL extracts features from structural and textual information embedded in the BC/MC packets.
This paper proposed a deep-learning-based approach to predict the reachability of inputs before executing the target program, helping DGF filtering out the unreachable ones to boost the performance of fuzzing.
The paper proposes a cost-effective (no real car needed) and automatic (no human intervention required) solution CANHUNTER to reverse engineer CAN bus commands via analyzing mobile apps associated with cars.
The paper presents a novel attack for detecting the presence of an active TCP connection between a remote Linux server and an arbitrary client machine.
