Zeming Wei
PulseAugur coverage of Zeming Wei — every cluster mentioning Zeming Wei across labs, papers, and developer communities, ranked by signal.
-
New framework enhances AI model robustness against multi-attack adversarial training
Researchers have developed a new framework called Calibrated Adversarial Sampling (CAS) to improve the robustness of Deep Neural Networks (DNNs) against multiple types of adversarial attacks. CAS reformulates the multi-…
-
New defense secures multi-agent LLM systems against misinformation
Researchers have developed a new defense mechanism for multi-agent systems (MAS) that utilize large language models (LLMs). This method addresses the issue of adversarial agents injecting misleading information that can…
-
New SMI method offers reliable, efficient auditing of unlearned AI models
Researchers have introduced Statistical Membership Inference (SMI), a novel framework for auditing machine unlearning processes. Traditional methods using Membership Inference Attacks (MIAs) often overestimate unlearnin…