2 papers
cs.CR2026
Benign Inputs, Harmful Outputs: Cross-Modal Jailbreaking via Distributed Semantic Recomposition
Yani Wang, Yilong Yang, Yang Liu +3
Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable capabilities in content synthesis and autonomous reasoning. Previous safety guardrails are primarily…
cs.CR2026
Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction
Huajie Chen, Tianqing Zhu, Hailin Yang +7
Watermarking has emerged as a key defense against the misuse of machine-generated images (MGIs). Yet the robustness of these protections remains underexplored. To reveal the limits…