Search Results for author:
Found 3 papers, 1 papers with code
Backdoor Attack with Sparse and Invisible Trigger
More importantly, it is not feasible to simply combine existing methods to design an effective sparse and invisible backdoor attack.
Catch You and I Can: Revealing Source Voiceprint Against Voice Conversion
Voice conversion (VC) techniques can be abused by malicious parties to transform their audios to sound like a target speaker, making it hard for a human being or a speaker verification/identification system to trace the source speaker.
MARNET: Backdoor Attacks against Value-Decomposition Multi-Agent Reinforcement Learning
Recent works have revealed that backdoor attacks against Deep Reinforcement Learning (DRL) could lead to abnormal action selection of the agent, which may result in failure or even catastrophe in crucial decision processes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
