AI Security Podcast How Microsoft Uses AI for Threat Intelligence & Malware Analysis
26 snips
Oct 18, 2025 Thomas Roccia, a Senior Threat Researcher at Microsoft specializing in AI applications for malware analysis, discusses groundbreaking concepts like the 'Indicator of Prompt Compromise' (IOPC). He shares insights on his open-source projects, including NOVA, a tool to detect malicious prompts. The conversation explores using AI to track complex crypto laundering schemes, simplifying reverse engineering, and how AI enhances threat intelligence. Roccia also highlights the shift in skill accessibility, where advanced tasks become manageable for more professionals.
AI Snips
Chapters
Transcript
Episode notes
AI Accelerates Reverse Engineering
- Generative AI can automate time-consuming malware analysis and reverse engineering tasks.
- AI acts as an assistant to speed analysis but is not yet a flawless replacement for experts.
Agent Tracks $1.4B Bybit Heist
- Thomas built an agent to track the Bybit $1.4B crypto heist and follow the money across thousands of wallets.
- The agent assists analysts by fetching transactions and iteratively exploring wallets rather than ingesting the entire blockchain at once.
Query Blockchain In Managed Slices
- Feed agents manageable slices of blockchain context instead of the entire chain to avoid context-window limits.
- Query for focused transactions (e.g., top transfers) and iteratively expand analysis per wallet.