Pinned Loading

1. ASD ASD Public

   [CVPR 2023] Backdoor Defense via Adaptively Splitting Poisoned Dataset

   Python 49 6

2. Verbose_Images Verbose_Images Public

   [ICLR 2024] Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images

   Python 42 2

3. sail-sg/imperceptible-jailbreaks sail-sg/imperceptible-jailbreaks Public

   [ArXiv 2025] Imperceptible Jailbreaking against Large Language Models

   Python 25 5

4. IRBA IRBA Public

   [IEEE Transactions on Information Forensics & Security 2023] Imperceptible and Robust Backdoor Attack in 3D Point Cloud

   Python 12 1

5. sail-sg/P-DoS sail-sg/P-DoS Public

   [ArXiv 2025] Denial-of-Service Poisoning Attacks on Large Language Models

   Python 23 3

6. ADU-Bench ADU-Bench Public

   [ACL 2025] Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models

   Python 7