Modern image generators can produce complex visual artifacts, including diagrams, interfaces, and records that combine text, graphics, and layout to convey detailed information. They may refuse requests for overtly harmful imagery yet still generate artifacts that guide dangerous actions or support deception. We call t...
Zi-Hao Zhu, Yuansan Liu, Siwei Lyu et al.· 0 citations
Efficient-transformer research often motivates token pruning and adaptive computation with the claim that not all tokens require equal computational effort. We test this claim end to end using SEWN, a two-stream Transformer that routes tokens through either lightweight or full-capacity processing using a learned gate....
Sai Krishna Arthanari, JaeHyeong Chang, Chengzhe Sun et al.· 0 citations
DecFlowEdit is proposed, which decouples the optimal guidance scales for localization and for editing in flow-based generative models and first extracts an edit-relevant prior by temporally aggregating velocity differences evaluated without CFG, and then uses this prior to reweight the original updates under default CF...
Zhe-Yuan Zhan, Can Wang, Jia-Wei Chen et al.· arXiv.org· 0 citations
This paper introduces skill cascading attacks, a threat paradigm in which a malicious objective is distributed across multiple skills so that each modification looks benign in isolation, yet their combined execution is harmful.
Zi-Hao Zhu, Siwei Lyu, A. Bibi et al.· arXiv.org· 0 citations
PIVOT, a physics-grounded AIGC detector instantiated here for audio-video clips, that estimates physical quantities from video and audio, selects physical laws relevant to each clip, and verifies their measurable constraints, demonstrates the practical promise of physical-consistency verification as a structured and in...
Bo-Yuan Zheng, Kang-Ran Zhao, Xiao-Yu Zhang et al.· 0 citations
A multi-agent synthesis framework is developed that composes individually benign components into harmful scenarios and generates diverse DIH videos with explicit reasoning annotations, yielding a dataset of over 9,000 videos spanning visual-only and audio-visual settings.
Ruotong Wang, Zihao Zhu, Siwei Lyu 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.