Tiansheng Huang

5

Papers

111

Total Citations

Papers (5)

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

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

Personalized Privacy Protection Mask Against Unauthorized Facial Recognition

Adversarial Attention Perturbations for Large Object Detection Transformers

Resource-Efficient Transformer Pruning for Finetuning of Large Models