Adversarially Pretrained Transformers may be Universally Robust In-Context Learners
Authors: Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki | Published: 2025-05-20
PandaGuard: Systematic Evaluation of LLM Safety in the Era of Jailbreaking Attacks
Authors: Guobin Shen, Dongcheng Zhao, Linghao Feng, Xiang He, Jihang Wang, Sicheng Shen, Haibo Tong, Yiting Dong, Jindong Li, Xiang Zheng, Yi Zeng | Published: 2025-05-20
Fragments to Facts: Partial-Information Fragment Inference from LLMs
Authors: Lucas Rosenblatt, Bin Han, Robert Wolfe, Bill Howe | Published: 2025-05-20
FlowPure: Continuous Normalizing Flows for Adversarial Purification
Authors: Elias Collaert, Abel Rodríguez, Sander Joos, Lieven Desmet, Vera Rimmer | Published: 2025-05-19
Fixing 7,400 Bugs for 1$: Cheap Crash-Site Program Repair
Authors: Han Zheng, Ilia Shumailov, Tianqi Fan, Aiden Hall, Mathias Payer | Published: 2025-05-19
The Hidden Dangers of Browsing AI Agents
Authors: Mykyta Mudryi, Markiyan Chaklosh, Grzegorz Wójcik | Published: 2025-05-19
Evaluatiing the efficacy of LLM Safety Solutions : The Palit Benchmark Dataset
Authors: Sayon Palit, Daniel Woods | Published: 2025-05-19
From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents
Authors: Liangxuan Wu, Chao Wang, Tianming Liu, Yanjie Zhao, Haoyu Wang | Published: 2025-05-19
Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
Authors: Zi Liang, Haibo Hu, Qingqing Ye, Yaxin Xiao, Ronghua Li | Published: 2025-05-19
Malware families discovery via Open-Set Recognition on Android manifest permissions
Authors: Filippo Leveni, Matteo Mistura, Francesco Iubatti, Carmine Giangregorio, Nicolò Pastore, Cesare Alippi, Giacomo Boracchi | Published: 2025-05-19