Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints
Authors: Zirui Huang, Yunlong Mao, Wei Tong, Tingting Wu, Xin Ge, Sheng Zhong | Published: 2026-08-03
プロンプトリーキング
MIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information Bottleneck
Authors: Dongyi Liu, Haixing He, Xiaobao Wu, Jia Li | Published: 2026-07-30
Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions
Authors: Shi Lin, Peng Qian, Dinghao Liu, Renjie Sun, Sifan Wu, Dezhang Kong, Chenpei Wang, Xun Wang | Published: 2026-07-29
Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering
Authors: Maria Rosaria Briglia, Igor Maljkovic, Antonio Emanuele Cinà, Luca Oneto, Iacopo Masi, Fabio Roli | Published: 2026-07-28
When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs
Authors: Tong Zhang, Zexin Li, Simin Chen, Yun Peng | Published: 2026-07-27
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
Authors: Yuxi Li, Zhibo Zhang, Kailong Wang, Xingshuo Han, Ling Shi, Haoyu Wang | Published: 2026-07-22
The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
Authors: Gjergji Kasneci, Enkelejda Kasneci | Published: 2026-07-21
Data Leakage Prevention in Agentic Applications via Preemptive Hardening
Authors: Akansha Shukla, Emily Bellov, Parth Atulbhai Gandhi, Yuval Elovici, Asaf Shabtai | Published: 2026-07-21
Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models
Authors: Dongdong Yang, Deyue Zhang, Zhao Liu, Zonghao Ying, Wenzhuo Xu, Jiankai Jin, Xiangzheng Zhang, Quanchen Zou | Published: 2026-07-20
Open-Source Intelligence for Code Provenance and the Security Patterns that Separate Human and Large-Language-Model Implementations of Common Programming Tasks
Authors: Mohammadreza Rashidi | Published: 2026-07-14