Follow the Gradient: Tracing Safety Degradation Back to Training Data
Authors: Saket Reddy, Amro Abbas, Anshuman Suri, Ari Morcos, David Schwab, Pratyush Maini | Published: 2026-10-27
文献データベース
Autonomous fixed-wing interception using reinforcement learning
Authors: Daan van Hamersveld, Ewoud Smeur, Iurii Kriachko | Published: 2026-10-27
When Is a Relation Worth Trusting? Manipulation Costs, Exposure, and the Trust Trap in Multi-Relational Graph Learning
Authors: Vincess Dongmo, Astride Melvin Fokam Ninyim | Published: 2026-10-27
PrivacyEvalClaw: A Tool-Augmented Deliberative Agent for Auditing Privacy Leakage in LLM Jailbreak Responses
Authors: Krishna Kanth Nakka, Yujun Wang, Shijie Zhou, Tu Nguyen, Gabriele Gelardi, Xuebing Zhou | Published: 2026-10-27
What Victims Take Away: Attack Reuse and Defense Revision after Prompt-Injection Attacks
Authors: Zihan Chen, Lei Nico Zheng, Di Zhu | Published: 2026-10-27
Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models
Authors: Amine Lbath, Massih-Reza Amini | Published: 2026-10-26
CLOSURE: Cross-Channel Closure for Multivariate Time Series Anomaly Detection
Authors: Fan Xu, Hao Wu, Zhi Song, Hanbo Huang, Wenzhuo Ma, Nan Wang, Wei Gong, Xibin Zhao | Published: 2026-10-26
The Agent in the Middle: How AI-Mediated Access Reshapes Web Vulnerability Exploitation
Authors: Ruozhao Yang, Jiongchi Yu, Ming Hu, Xiaofei Xie | Published: 2026-10-26
JANUS: Synthesizing Cross-Layer Defenses Against Web Deserialization Attacks
Authors: Ruozhao Yang, Minglang Li, Jiongchi Yu, Xinfeng Li, Xiaofei Xie | Published: 2026-10-26
CANS: Capability-Preserving Neuron Steering for Large Language Models
Authors: Yucheng Wu, Chengyi Xie, Chenpeng Wang, Liangming Pan | Published: 2026-10-26