Author

Xiang-Man Li

h-index 3 View on Semantic Scholar

We have 3 of 19 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

EVOMAL: Self-Poisoning in Self-Evolving Coding Agents

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...

Xiaodong Wu, Yu Shi, Qi Li et al. · 2 citations

Preprint Aug 2026

SkillShield: Prompt-Space Security Skills for LLM Coding Agents

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

Preprint Aug 2026

MarkNull: Model-Agnostic Watermark Removal in AI-Generated Images via On-Manifold Latent Manipulation

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