When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs
Authors: Tong Zhang, Zexin Li, Simin Chen, Yun Peng | Published: 2026-07-27
AIセキュリティポータルbot
DeepFaith: Evidence-Grounded LLMs for Faithful Incident Reporting in Multi-Stage APT Defense
Authors: Trung V. Phan, Tri Gia Nguyen, Thomas Bauschert | Published: 2026-07-27
Beyond Aggregate Risk: Role-Stratified Conformal Risk Control for LLM Tool Calls
Authors: Md Ashikur Rahman, Md Arifur Rahman, Niamul Hassan Samin, Khandaker Rifah Tasnia, Sifat Rahman Ahona, Juena Ahmed Noshin | Published: 2026-07-27
Gubernaut: A Deterministic Homeostatic Controller for Affect-Regulated LLM Agents, Validated Across Independent Model Families
Authors: Dushyant Sharma | Published: 2026-07-27
Just Testing, Move Along: Evasion of LLM-based System Log Interpretation by Prompt Injection
Authors: Max Landauer, Florian Skopik, Markus Wurzenberger, Franciszek Górski, Mateusz Krzysztoń | Published: 2026-07-27
A Cybersecurity MLPS Large Language Model with Multi-Path Retrieval Fusion
Authors: Qian Li, Zhenyan Qi, Liang Shen, Yuan Zhang, Yifan Wan, Junyuan Ma, Yining Hu | Published: 2026-07-27
Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation
Authors: Mohan Manivannan, Dalal Alharthi | Published: 2026-07-27
Tag Questions and the Generational Reversal of Sycophancy Across 45 Language Models
Authors: Tapan Parikh | Published: 2026-07-27
Understanding Machine Unlearning Through the Lens of Mode Connectivity
Authors: Jiali Cheng, Hadi Amiri | Published: 2026-07-27
V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure
Authors: Zhetong Zhang, Honghao Fu, Miao Xu, Yiwei Wang, Yujun Cai | Published: 2026-07-23