Fanxiao Li

The paper introduces REFORGE, a black-box red-teaming framework that uses adversarial image prompts to reveal persistent vulnerabilities in current Image Generation Model Unlearning (IGMU) methods.

The paper introduces FlowSteer, a prompt-only attack that exploits vulnerabilities in how multi-agent LLM systems plan workflows, significantly increasing the success rate of malicious signal propagation.

The paper introduces EvoNote, a self-evolving agentic framework that significantly improves the generation of evidence-grounded health community notes by utilizing an accumulated memory of past misinformation correction experiences.