Jiawang Bai

7

Papers

68

Total Citations

Papers (7)

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP

Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers

Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips

Improving Vision Transformers by Revisiting High-Frequency Components

Targeted Attack for Deep Hashing based Retrieval

GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph