Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models
搜索或加速:基于置信度切换的位置束搜索用于扩散语言模型
Mingyu Cao, Alvaro H. C. Correia, Christos Louizos, Shiwei Liu, Lu Yin
机构
*
University of Surrey(塞拉利昂大学)
;
Qualcomm AI Research. Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc.(高通人工智能研究)
;
ELLIS Institute Tübingen(图宾根ELLIS研究所)
;
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
;
Tübingen AI Center(图宾根人工智能中心)
Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemes
现成的图像到图像模型就是对抗图像保护方案所需的一切
Xavier Pleimling, Sifat Muhammad Abdullah, Gunjan Balde, Peng Gao, Mainack Mondal, Murtuza Jadliwala, Bimal Viswanath
机构
*
University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校)
专题命中
仓库级理解
:repository(abstract);分类 cs.AI
AI总结
现成的图像到图像模型可有效对抗图像保护方案,揭示其存在广泛漏洞,需建立更坚固的防御措施。
CommentsThis work has been accepted for publication at the IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). The final version will be available on IEEE Xplore. To IEEE SaTML 2026