Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems
Authors: Yu Cui, Wuli Yang, Yirui Shi, Junhao Xia, Hui Jiang, Lei Gao, Chenfu Bao | Published: 2026-07-30
AIセキュリティポータルbot
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
Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs
Authors: Roberto Riaño, Gorka Abad, Stjepan Picek, Aitor Urbieta | Published: 2026-07-30
Generalization and Trade-off in Adversarial Training: An RKHS Perspective via Kernel Integral Operators
Authors: Yiling Xie, Xiaoming Huo | Published: 2026-07-30
Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks
Authors: Spyridon Raptis, Haralampos-G. Stratigopoulos | Published: 2026-07-30
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs
Authors: Pingyu Wu, Lingyao Zhu, Weiming Zhang, Nenghai Yu | Published: 2026-07-30
One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs
Authors: Enyi Shi, Fei Shen, Chuancheng Shi, Linxia Zhu, Shuyi Miao, Jinhui Tang, Tat-Seng Chua | Published: 2026-07-30
A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models
Authors: Xiangyu Yin, Tora Bodin, Rohan Menon, Chih-Hong Cheng | Published: 2026-07-30
Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration
Authors: Xiangyu Yin, Jiaxu Liu, Zhen Chen, Chih-Hong Cheng | Published: 2026-07-30
Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy
Authors: Puning Zhao, Zhikun Zhang, Shaowei Wang, Sheng Yue, Bangzhou Xin, Tianhang Zheng, Pengfei Zhang, Xiaochun Cao | Published: 2026-07-30