AIセキュリティポータルbot

GAVEL: Towards rule-based safety through activation monitoring

Authors: Shir Rozenfeld, Rahul Pankajakshan, Itay Zloczower, Eyal Lenga, Gilad Gressel, Yisroel Mirsky | Published: 2026-01-27
LLM性能評価
インダイレクトプロンプトインジェクション
データ生成手法

RvB: Automating AI System Hardening via Iterative Red-Blue Games

Authors: Lige Huang, Zicheng Liu, Jie Zhang, Lewen Yan, Dongrui Liu, Jing Shao | Published: 2026-01-27
AIシステムの関係性
敵対的学習
自動脆弱性修復

CHEHAB RL: Learning to Optimize Fully Homomorphic Encryption Computations

Authors: Bilel Sefsaf, Abderraouf Dandani, Abdessamed Seddiki, Arab Mohammed, Eduardo Chielle, Michail Maniatakos, Riyadh Baghdadi | Published: 2026-01-27
FHEの最適化
コード生成手法
強化学習

AI-driven Intrusion Detection for UAV in Smart Urban Ecosystems: A Comprehensive Survey

Authors: Abdullah Khanfor, Raby Hamadi, Noureddine Lasla, Hakim Ghazzai | Published: 2026-01-27
UAVセキュリティ
データ収集
機械学習アルゴリズム

LLMs Can Unlearn Refusal with Only 1,000 Benign Samples

Authors: Yangyang Guo, Ziwei Xu, Si Liu, Zhiming Zheng, Mohan Kankanhalli | Published: 2026-01-27
LLM活用
大規模言語モデル
安全性評価

AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection

Authors: Wachiraphan Charoenwet, Kla Tantithamthavorn, Patanamon Thongtanunam, Hong Yi Lin, Minwoo Jeong, Ming Wu | Published: 2026-01-27
LLM活用
セキュリティ保証
脆弱性検出手法

Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models

Authors: Harsh Chaudhari, Ethan Rathbum, Hanna Foerster, Jamie Hayes, Matthew Jagielski, Milad Nasr, Ilia Shumailov, Alina Oprea | Published: 2026-01-27
LLM活用
データ汚染検出
出力の有害度の算出

$α^3$-SecBench: A Large-Scale Evaluation Suite of Security, Resilience, and Trust for LLM-based UAV Agents over 6G Networks

Authors: Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah | Published: 2026-01-26
LLM活用
セキュリティ保証
プロンプトインジェクション

Scaling up Privacy-Preserving ML: A CKKS Implementation of Llama-2-7B

Authors: Jaiyoung Park, Sejin Park, Jai Hyun Park, Jung Ho Ahn, Jung Hee Cheon, Guillaume Hanrot, Jung Woo Kim, Minje Park, Damien Stehlé | Published: 2026-01-26
LLM活用
プロンプトリーキング
線形代数最適化

Mitigating the OWASP Top 10 For Large Language Models Applications using Intelligent Agents

Authors: Mohammad Fasha, Faisal Abul Rub, Nasim Matar, Bilal Sowan, Mohammad Al Khaldy | Published: 2026-01-26
LLM活用
RAG
セキュリティ保証