Jie Zhang

Mitigating Watermark Forgery in Generative Models via Randomized Key Selection

Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning

Warfare: Breaking the Watermark Protection of AI-Generated Content

OBJVANISH: PHYSICALLY REALIZABLE TEXT-TO-3D ADV. GENERATION OF LIDAR-INVISIBLE OBJECTS

Enhancing Adversarial Robustness of Vision Language Models via Adversarial Mixture Prompt Tuning

Every Subtlety Counts: Fine-grained Person Independence Micro-Action Recognition via Distributionally Robust Optimization

Fair-SP: Capturing Pluralistic Social Equity Preferences Through Synthetic Data

Mask Image Watermarking

DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers

VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking

Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Models

Warfare: Breaking the Watermark Protection of AI-Generated Content

Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems

PRIME: Protect Your Videos From Malicious Editing

EditMark: Training-free and Harmless Watermark for Large Language Models

SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution