InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models
Authors: Chengyin Hu, Dingyi Lu, Jiaju Han, Xiang Chen, Weiwen Shi, Jiahuan Long, Yiwei Wei, Jiujiang Guo | Published: 2026-09-02
文献データベース
ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language Models
Authors: Da Cheng Gu, Yifei Dong, Xinghao Yang, Yongshun Gong, Wei Liu | Published: 2026-09-02
WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading
Authors: Gang-Hyun Park, Ju-Hyeong Lee, Hee-Youl Kwak, Dae-Young Yun | Published: 2026-09-02
FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs
Authors: Zhengyi Jin, Ru Zhang, Xiao Chen, Xinbo Liu, Jiaxuan Lin, Jia Huang, Jianyi Liu, Zhen Yang | Published: 2026-09-02
OBJECTION! Lawyer Agents Mitigate Guilty Bias in Legal Judgment Prediction
Authors: Jaehoon Jeong, Jay-Yoon Lee | Published: 2026-09-02
C$^{3}$T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees
Authors: S M Rafiuddin, Atriya Sen | Published: 2026-09-02
Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models
Authors: Tianqi Xiao, Shiyao Cui, Minghao Zhang, Junxiao Yang, Renmiao Chen | Published: 2026-09-02
When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning
Authors: Yitong Guo, Xiaoyi Chen, Siyuan Zhang, Xiaofeng Wang, Haixu Tang | Published: 2026-09-01
Position: Privacy Is a Claim, Not a Property of Synthetic Data
Authors: Jiachen Zhao, Antonia Januszewicz, Taeho Jung | Published: 2026-09-01
Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents
Authors: Liming Pu, Xiaoxia Li, Yifu Liu, Teng Cao, Bin Yang | Published: 2026-09-01