4 citations · 7 across the 4 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2025
Learning-Based Automated Adversarial Red-Teaming for Robustness Evaluation of Large Language Models
Zhang Wei, Hanxuan Chen, Peilu Hu +19
Red-teaming is becoming a central part of large language model (LLM) safety evaluation, yet current practice still relies heavily on expert-written prompts or fixed benchmark suite…
cs.CR2024★ 4 cited
Jailbreaking and Mitigation of Vulnerabilities in Large Language Models
Benji Peng, Hanxuan Chen, Keyu Chen +12
Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthc…