arXiv Brief — 2026-10-27
New papers on agents as operating systems, LLM-based vulnerability detection, RAG poisoning, LLM agent root cause analysis harnesses, and agentic message boards.
Reverse-Engineering
arXiv Brief — 2026-10-26
Automated protocol reverse engineering via tree-of-thought search, incomparable minima in tool authorization for agents, and decode-time provenance binding to stop MCP indirect injection.
arXiv Brief — 2026-10-16
New papers on bypassing TEE-shielded LLM partition, reverse-engineering iOS location protobufs, localising LLM agent failures, steering LLM agents, and forensic analysis of the HackRF One.
Conference Brief — 2026-10-09
New tools for discovering logic vulnerabilities in QUIC, scan-cycle fuzzing for industrial control systems, and neural decompilation recovering user-defined types.
Conference Brief — 2026-10-06
A batch of papers from NDSS.