Agentic Cyber Defense Against AI-Enabled Attacks - Research Digest

OpenDraco: A Platform for Engineering and Experimenting with Configurable Multi-Agent Architectures for Software Engineering

Xiang Feng Ye Pan, Vincenzo De Martino, Matias Martinez

Source: arxiv

Trusting the Tool: Asymmetric Deference of LLM Vulnerability Auditors to Static-Analysis Evidence

ZhiHong Liu, Shuyao Gao

Source: arxiv

Automated Multi-Line Bug Repair Using Model Checker Aided LLMs: A Case Study on RISC-V Processors

Debleena Das, Chandan Kumar Jha, Muhammad Hassan, Rolf Drechsler, Ansuman Banerjee, Subhra K. Das, Amlan Chakrabarti

Source: arxiv

StateMirror: Pre-Execution Detection of Hallucinated Tool Calls in Coding Agents

Shiwen Shan, Yintong Huo, Zhiying Wu, Yuxin Su

Source: arxiv Must Read

Lessons Outlive Their Failures: A Case Study of Rules for AI Coding Agents

Hassan Hassanzadeh Aliabadi

Source: arxiv Must Read

On Task, Off Track: Benchmarking LLM and Agent Robustness to Near-Target Prompt Injection

Yuyang Gong, Zihao Wang, Jiawei Liu, XiaoFeng Wang

Source: arxiv Must Read

Reimagining Enterprise RAG for Multi-Agent Systems: A Knowledge Layer That Organizes Before It Retrieves

Garima Agrawal, Prasun Das, Akshay Sarvade, Priyanka L, Minisha N, Sravani Joshna, Hemath Manivannan, Lavanya Korada, Sambhrit Pattanayak, Srashti Gupta, Siddu R, Prasad Kalyanasundaram

Source: arxiv Must Read

Tool-Calling LLM Agents Under Realistic MCP Faults: Scale Does Not Purchase Fault Tolerance

Antonio Ken Iannillo, Joshua Segun Owotogbe, Roberto Natella, Francesco Avallone, Kristina Kudryavtseva, Indika Kumara

Source: arxiv Must Read

AquaSense-ICS: A Hybrid Real-Simulated Cyber-Physical Dataset and Leakage-Aware Benchmark for Smart Water Quality Monitoring and Attack Detection

Amal Neji, Mohamed Fourati, Lamia Chaari Fourati

Source: arxiv Must Read

Detecting Insecure Compositions of Clean Agent Skills via Capability-Flow Graph Analysis

Yihao Li, Chuanpu Fu, Yizhou Zhao, Miao Chen, Qi Li, Ke Xu

Source: arxiv Must Read