Language-model agents are vulnerable to indirect prompt injection (IPI) during tool use: adversarial instructions hidden in untrusted tool outputs can covertly redirect legitimate task execution. Existing work often trains and evaluates defenses against fixed attacks that do not adapt to the defender's behavior, so the...
Bo-Yang Zhang, Qing-Xin Xiao, Lingwei Dang et al.· 2 citations
This paper proposes CRFormer, a single-stage Transformer network for blind visible watermark removal that replaces the CNN backbone with a full Transformer to model watermark regions of arbitrary spatial extent and introduces a deformable convolution feed-forward network that restores spatial perception and integrates...
Yun Hao, Jiaju Wu, Rui Sun et al.· Neural Networks· 0 citations
Roomer is presented, a reflective repair framework that casts local violations as sparse, object-grounded repair problems and repairs residual violations while preserving valid regions, improves physical validity and usability, and transfers across external generators.
Lingwei Dang, Ziyan Qiu, Jiajia Cheng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.