Li Huang
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
DeepGuard introduces a novel multi-layer semantic aggregation framework to enhance secure code generation by collecting vulnerability cues from multiple upper layers of LLMs, significantly improving security while maintaining functional correctness.
TEMPLATEFUZZ is a fine-grained fuzzing framework that systematically tests chat templates to find vulnerabilities in LLMs, achieving high jailbreak success rates with minimal performance degradation.
Papers
TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs
Qingchao Shen, Zibo Xiao, Lili Huang, Enwei Hu +2 more
TEMPLATEFUZZ is a fine-grained fuzzing framework that systematically tests chat templates to find vulnerabilities in LLMs, achieving high jailbreak success rates with minimal performance degradation.