Weisen Jiang
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
MetaMoE introduces a privacy-preserving framework that unifies independently trained, domain-specialized experts into a single Mixture-of-Experts (MoE) model using diversity-aware proxy data.
SPARD is a defense framework that uses Safety-Projected Alternating optimization and Relevance-Diversity data selection to mitigate harmful fine-tuning attacks that undermine LLM safety.
SPARD is a defense framework that uses Safety-Projected Alternating optimization and Relevance-Diversity data selection to protect large language models from harmful fine-tuning attacks, achieving superior defense performance.
Papers
SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection
Shuhao Chen, Weisen Jiang, Yeqi Gong, Shengda Luo +4 more
SPARD is a defense framework that uses Safety-Projected Alternating optimization and Relevance-Diversity data selection to mitigate harmful fine-tuning attacks that undermine LLM safety.