Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environments
Kunal Mukherjee, Spandan Mukherjee
Trusted Execution Environments (TEEs) (e.g., Intel SGX and ArmTrustZone) aim to protect sensitive computation from a compromised operating system, yet real deployments remain vulne…
cs.CR2025
LLM-driven Provenance Forensics for Threat Investigation and Detection
Kunal Mukherjee, Murat Kantarcioglu
We introduce PROVSEEK, an LLM-powered agentic framework for automated provenance-driven forensic analysis and threat intelligence extraction. PROVSEEK employs specialized toolchain…