データ毒性

Agentic AI as a Cybersecurity Attack Surface: Threats, Exploits, and Defenses in Runtime Supply Chains

Authors: Xiaochong Jiang, Shiqi Yang, Wenting Yang, Yichen Liu, Cheng Ji | Published: 2026-02-23
RAGへのポイズニング攻撃
データ毒性
脆弱性分析

BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models

Authors: Zihan Wang, Hongwei Li, Rui Zhang, Wenbo Jiang, Guowen Xu | Published: 2026-02-05
LLM性能評価
データ毒性
大規模言語モデル

Fake or Real: The Impostor Hunt in Texts for Space Operations

Authors: Agata Kaczmarek, Dawid Płudowski, Piotr Wilczyński, Przemysław Biecek, Krzysztof Kotowski, Ramez Shendy, Jakub Nalepa, Artur Janicki, Evridiki Ntagiou | Published: 2025-07-17 | Updated: 2025-07-21
データ毒性
偽情報の検出
出力の有害度の算出

Instance-Level Data-Use Auditing of Visual ML Models

Authors: Zonghao Huang, Neil Zhenqiang Gong, Michael K. Reiter | Published: 2025-03-28 | Updated: 2025-09-16
データ毒性
モデル抽出攻撃の検知
透かし技術