Tiansheng Huang

5

Papers

52

Total Citations

Papers (5)

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

Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training