Yuming

This paper proposes a comprehensive taxonomy (SLOT) to systematically categorize security risks, attacks, and defenses specific to Retrieval-Augmented Generation (RAG), clarifying that these risks are distinct from inherent LLM flaws.

GoAT-X introduces a novel framework that structures cross-chain smart contract auditing as a Graph of Auditing Thoughts, significantly improving the detection of complex, semantic vulnerabilities in multi-chain token transactions.

SkillScope introduces a graph-based framework to enforce fine-grained least-privilege in LLM Agent Skills, significantly reducing over-privileged actions while maintaining task functionality.

The paper introduces a 'replication-first' paradigm for LLM behavioral benchmarking, demonstrating that this rigorous approach uncovers significant, non-obvious performance drops between successive model versions, such as a notable decline in advice-restraint for GPT-5.

The paper introduces PRISM, a novel representation learning framework that learns isometric embeddings by explicitly modeling the intrinsic geodesic metric of 3D surfaces, achieving superior performance on various geometric tasks.