13 papers
Targeted Downstream-Agnostic Attack
Zhuxin Lei, Ziyuan Yang, Yi Zhang
Recently, pre-trained encoders have gained widespread use due to their strong capability in representation extraction. However, they are vulnerable to downstream-agnostic attacks (…
Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent Framework
Mengyu Sun, Ziyuan Yang, Zunlong Zhou +3
Diffusion models (DMs) are widely used for text-to-image generation, but their strong generative capabilities also raise concerns about unsafe or undesirable content. Concept erasu…
Catching the Infection Before It Spreads: Foresight-Guided Defense in Multi-Agent Systems
Yue Ma, Ziyuan Yang, Yi Zhang
Large multimodal model-based Multi-Agent Systems (MASs) enable collaborative complex problem solving through specialized agents. However, MASs are vulnerable to infectious jailbrea…
PrismAgent: Illuminating Harm in Memes via a Zero-Shot Interpretable Multi-Agent Framework
Zihan Ding, Ziyuan Yang, Yi Zhang
The rapid spread of memes makes harmful content detection increasingly crucial, as effective identification can curb the circulation of misinformation. However, existing methods re…
From Static Analysis to Audience Dissemination: A Training-Free Multimodal Controversy Detection Multi-Agent Framework
Zihan Ding, Ziyuan Yang, Yi Zhang
Multimodal controversy detection (MCD) identifies controversial content in videos and their associated user comments, to support risk management for social video platforms.Prior re…
Trust the Unreliability: Inward Backward Dynamic Unreliability Driven Coreset Selection for Medical Image Classification
Yan Liang, Ziyuan Yang, Zhuxin Lei +3
Efficiently managing and utilizing large-scale medical imaging datasets with limited resources presents significant challenges. While coreset selection helps reduce computational c…