Image watermarking enables provenance tracing for photorealistic images generated by diffusion models. However, state-of-the-art (SOTA) removal attacks can suppress embedded signals with little perceptual degradation. This vulnerability limits the effectiveness of watermarks for intellectual property protection and mis...
Jie Cao, Qi Li, Chaklam Cheong et al.· 0 citations
Self-evolving LLM coding agents write their own tools by imitating retrieved skills from shared skill libraries. We identify a vulnerability in this loop: during authoring, a retrieved malicious skill can become the template for a new skill that preserves the payload. We call this self-poisoning: the agent authors, sto...
SkillShield is introduced, a system-prompt defense that synthesizes security skills offline from known attacks or recorded agent failures to prevent harmful actions and malware generation for LLM coding agents.
Xiaodong Wu, Zhimin Zhao, Qi Li et al.· 0 citations
This paper proposes MarkNull, a model-agnostic watermark removal attack via on-manifold latent manipulation that successfully compromise Google's SynthID-Image system while preserving high visual quality and transfer effectively to video watermarking.
Jie Cao, Qi Li, Zelin Zhang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
