AIエージェント間の連携に関する脅威
本記事では、OWASP Foundationによる「OWASP Top 10 for Agentic Applications 2026 」に記載されている脅威やその対策について最新の研究動向を交えながら解説します。特に、本記事では AIエージェント間の連携に関連する3つの脅威を扱います。
SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment
Authors: Xixun Lin, Yang Liu, Yancheng Chen, Yongxuan Wu, Yucheng Ning, Yilong Liu, Nan Sun, Shun Zhang, Bin Chong, Chuan Zhou, Yanan Cao, Li Guo | Published: 2026-04-15
TimeMark: A Trustworthy Time Watermarking Framework for Exact Generation-Time Recovery from AIGC
Authors: Shangkun Che, Silin Du, Ge Gao | Published: 2026-04-14
Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference
Authors: Anes Abdennebi, Nadjia Kara, Laaziz Lahlou | Published: 2026-04-14
ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
Authors: Wei Zhao, Zhe Li, Peixin Zhang, Jun Sun | Published: 2026-04-13
Towards Automated Pentesting with Large Language Models
Authors: Ricardo Bessa, Rui Claro, João Trindade, João Lourenço | Published: 2026-04-13
A Synthetic Conversational Smishing Dataset for Social Engineering Detection
Authors: Carl Lochstampfor, Ayan Roy | Published: 2026-04-13
GPU Acceleration of Sparse Fully Homomorphic Encrypted DNNs
Authors: Lara D'Agata, Carlos Agulló-Domingo, Óscar Vera-López, Kaustubh Shivdikar, Ardhi W. B. Yudha, Ferhat Yaman, David Kaeli, José L. Abellán, Ian Colbert, José Cano | Published: 2026-04-13
RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience
Authors: Hanbo Huang, Xuan Gong, Yiran Zhang, Hao Zheng, Shiyu Liang | Published: 2026-04-13
RedShell: A Generative AI-Based Approach to Ethical Hacking
Authors: Ricardo Bessa, Rui Claro, João Trindade, João Lourenço | Published: 2026-04-13