Literature Database

Explainable Rule Mining of IPv6 Extension-Header Presence Patterns from Paired-Vantage Captures

Authors: Priyanka Sinha, Nikolaos Kekatos, Stylianos Basagiannis, Antonio Anastasio Bruto da Costa, Alexios Lekidis, Pabitra Mitra, Tom Nianios, Elpiniki Papageorgiou | Published: 2026-10-06
Data Flow Analysis
Network Traffic Analysis
Time-Related Features
2026.10.06 2026.10.08
Literature Database

ASCENT: First-Order Optimal Fine-Tuning with Recalibration for Safety–Utility Co-Enhancement

Authors: Weiwei Qi, Chongyu Wang, Tianhang Zheng, Zefeng Wu, Zhilin Guo, Xiaojun Jia, Zhongjie Ba, Kui Ren | Published: 2026-10-06
Prompt Injection
安全性と競争力
評価基準
2026.10.06 2026.10.08
Literature Database

Preparing an AI-Augmented SIEM for the EU Cyber Resilience Act: A Practitioner Case Study

Authors: Georgios Koutidis, Nikolaos Kekatos, Marina Korgiala-Karyda, Alexios Lekidis, Tom Nianios | Published: 2026-10-06
Cybersecurity
製品安全性
評価基準
2026.10.06 2026.10.08
Literature Database

Adversarially Trained Linear Transformers Are Optimal Robust In-Context Learners for Gaussian Mixtures

Authors: Soichiro Kumano | Published: 2026-10-06
Model Performance Evaluation
Adversarial Learning
Deep Learning
2026.10.06 2026.10.08
Literature Database

The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models

Authors: Yibo Zhang, Tianrong Guan, Liang Lin, Puze Wang, Jin Wang, Qingsong Wen | Published: 2026-10-06
トリガー選択戦略
Backdoor Detection
Backdoor Attack
2026.10.06 2026.10.08
Literature Database

Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security

Authors: Shaswata Mitra, Raj Patel, Subash Neupane, Sudip Mittal, Md Rayhanur Rahman, Shahram Rahimi | Published: 2026-10-06
Indirect Prompt Injection
Attack Scenario Analysis
Vulnerability Assessment Method
2026.10.06 2026.10.08
Literature Database

Does On-Policy Distillation for Safety Pose Backdoor Risks?

Authors: Jian Luo, Kehan Qi, Qingqiao Hu, Meilong Xu, Jiacheng Qiu, Weimin Lyu, Jiawei Zhou, Chao Chen | Published: 2026-10-06
Model Performance Evaluation
Calculation of Output Harmfulness
Trade-Off Between Safety And Usability
2026.10.06 2026.10.08
Literature Database

SkillPoison: Progressive Skill Poisoning via Successful Experiences

Authors: Lizhi Zhang, Xin He, Dianxuan Fu, Yuyuan Feng, Jiatong Li, Qi Wang, Xin Wang, Qinggang Zhang | Published: 2026-10-06
Poisoning attack on RAG
成功帰属
Behavior Analysis Method
2026.10.06 2026.10.08
Literature Database

HarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent Harnesses?

Authors: Zhengyang Zhu, Liming Huang, Runmin Ji, Mingxi Ye, Zihan Zhou, Hanyang Guo, Jingwen Wu, Yuhan Ye, Yuming Feng, Hong-Ning Dai, Zibin Zheng | Published: 2026-10-06
セキュリティ課題
Evaluation Method
Defense Mechanism
2026.10.06 2026.10.08
Literature Database

TranScope: What the Software Hides About LLM Training Data, the Hardware Reveals at Scale, and Accelerators Magnify

Authors: Joshua Kalyanapu, Darsh Asher, Kaushal Mhapsekar, Bita Aslrousta, Rushiraj Chaitanyakumar Sheth, Maharshi Mukeshkumar Oza, Achyuta Kannan, Samira Mirbagher Ajorpaz | Published: 2026-10-05
ハードウェアセキュリティ検証
Prompt leaking
Model Performance Evaluation
2026.10.05 2026.10.07
Literature Database
Next page