Picture for Zhan Qin

Zhan Qin

PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark

Add code
Aug 10, 2024
Viaarxiv icon

Defending Jailbreak Attack in VLMs via Cross-modality Information Detector

Add code
Aug 01, 2024
Viaarxiv icon

TAPI: Towards Target-Specific and Adversarial Prompt Injection against Code LLMs

Add code
Jul 12, 2024
Viaarxiv icon

Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning

Add code
Jul 06, 2024
Viaarxiv icon

Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Models

Add code
Jun 24, 2024
Viaarxiv icon

A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions

Add code
Jun 06, 2024
Viaarxiv icon

Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution

Add code
May 08, 2024
Viaarxiv icon

Going Proactive and Explanatory Against Malware Concept Drift

Add code
May 07, 2024
Viaarxiv icon

Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models

Add code
May 07, 2024
Viaarxiv icon

A Causal Explainable Guardrails for Large Language Models

Add code
May 07, 2024
Viaarxiv icon