fine-tuning 1large language models 1risk detection 1safety assessment 1semantic analysis 1subspace alignment 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CR2026
DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection
Weiwei Qi, Zefeng Wu, Zhilin Guo +5
Most existing LLM safety evaluation and defense methods follow a static formulation: jailbreak vulnerabilities are evaluated with fixed attack methods, and guardrails are trained o…
cs.CR2026
DataShield: Uncovering Risky Fine-Tuning Data Across LLMs Through Consensus Subspace Alignment
Zefeng Wu, Weiwei Qi, Jielong Chen +6
The paper introduces DataShield, a framework that detects risky fine‑tuning data for large language models by aligning safety‑critical semantic subspaces across multiple safety‑ali…
cs.CR2026
Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models
Weiwei Qi, Zefeng Wu, Tianhang Zheng +4
Ensuring Large Language Model (LLM) safety is crucial, yet the lack of a clear understanding about safety mechanisms hinders the development of precise and reliable methodologies f…