Tiansheng Huang

TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs

Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation

Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation

Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning Attack

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models

PokéLLMon: A Grounding and Reasoning Benchmark for Large Language Models in Pokémon Battles