Agentic Cyber Defense Against AI-Enabled Attacks - Research Digest

MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems

Mohammad Kachuee, Phu Mon Htut, Sheng Li, Nikolaos Pappas, Miguel Ballesteros Martinez, Yassine Benajiba, Sujith Ravi, Dan Roth

Source: arxiv

Cryptographically Secure Agent-to-Agent Communication in Multi-Agent Systems

Karol Budzyn, Adrian Brodzik, Mateusz Szczepkowski

Source: arxiv

Securing Agentic Commerce Through Behavior-Aware Fraud Detection and Cybersecurity for Trusted AI-Agent Payment Authorization

Kayode L. Ogunsusi

Source: arxiv

SecODD: Adapting the Operational Design Domain from Driving Autonomy to Autonomous Cyber Defense

Jina Kang, Jeong-Han Yun, Hyesong Choi

Source: arxiv

Attention-based Classification for Indirect Prompt Injection

Amelia Kawasaki, Stefan Lee

Source: arxiv

RATION: Towards Quantitative Risk-Based Access Control for AI Agents

Yuntao Du, Harsh Chaudhari, Yuetian Chen, Ron Heichman, Ashish Jayamohan, Kumar Pallav, Mahim Patel, Kaiyuan Zhang, Kyle Polley, Jerry Ma, Ninghui Li

Source: arxiv

Honeypots for AI Agent Insider Threats

Jan Wehner, Jam Kraprayoon

Source: arxiv

SPIDES: Information-Flow Control for Browser Agents

Egor Zverev, Juhee Kim, Leon Trampert, Boris Köpf, Aashish Kolluri, Shruti Tople, Santiago Zanella-Béguelin

Source: arxiv

SpanGuard: Decoupling Instruction Localization from Authorization for Lightweight IPI Defense

Yinxiang Wang, Zehua Ma, Kejiang Chen, Weiming Zhang, Han Fang

Source: arxiv

GRAD: Graph-Structured Antibody Defense for LLM Agents

Tianqi Song, Jiawei Du, Xuemei Jia, Zheng Wang

Source: arxiv

KNOX: Hardware-assisted Regulatory Sandbox for Generative Models

Vasisht Duddu, Adam Caulfield, Xi He

Source: arxiv

Runtime Control for AI Agents: Closing the Evaluation--Execution Gap in Operational Workflows

Jayesh Bhadane, Ramachandra Yerramsetti, Rajesh Gupta, Sumit Kumar

Source: arxiv

Accountable partial understanding: securing the epistemic attack surface of agentic systems

Josiah Dykstra

Source: arxiv

Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise

Pedro H. Barcha Correia, Matheus Azevedo de Sá, Paulo H. Gomes de Senna, Giovanni Mandel Martignago, Victor Takashi Hayashi, Charles Christian Miers, Marcos A. Simplicio

Source: arxiv Must Read

After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents

Zhiyue Xu, Xukai Wang, Zhiyuan Huang, Mingjie Zhan, Jian Zhao, Xu-Yao Zhang

Source: arxiv Must Read

Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents

Farhan Zarif, Kazi Shahid Ahmed Galib, Synthia Akter Promi, Shabnam Sharmin Tarin, Ariyan Hossain, Sadif Ahmed, Farig Yousuf Sadeque

Source: arxiv Must Read

MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection

Songping Wang, Peiyang Li, Yi Huang, Fengting Li, Xuhao Ran, Yueming Lyu, Chao Feng, Caifeng Shan

Source: arxiv Must Read

Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning

Yuqi Jia, Hangsheng Zhang, Chenxi Liu, Junjie Liang, Xun Chen

Source: arxiv Must Read

AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment

Eric Zhang, Terry Jingchen Zhang, Chijioke Ugwuanyi, Jerick Shi, Bernhard Schölkopf, Zhijing Jin

Source: arxiv Must Read