Meng Xu
2 papers · Latest:
Cryptography & Security
Generate "Normal", Edit Poisoned: Branding Injection via Hint Embedding in Image Editing
This paper reveals a new vulnerability where hidden branding in images can be re-rendered by generative AI models during editing, even without explicit prompts.
2605.10600
Cryptography & SecurityContextualizing Sink Knowledge for Java Vulnerability Discovery
GONDAR is a sink-centric fuzzing framework that leverages API semantics and collaborative agents to find Java vulnerabilities more effectively.
2604.01645
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.