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
Fine-tuning large language models (LLMs) on domain-specific datasets has become a standard paradigm for adapting LLMs to specialized applications. However, recent work has shown th…
cs.AI2026
Long-Term Simulation Exposes Cognitive-Developmental Risks in AI Companions
Kaicheng Shen, Lingyu Li, Wen Wu +3
AI companions powered by large language models increasingly interact with cognition-developing users, including children and adolescents, creating risks that may accumulate over ti…