Exploit Intelligence with Agentic AI: Patch What Matters
Dmitrijs Trizna
BSides NYC 2025 (0x05) · Day 1 · Tech - Other
In an era where cyber threats are escalating in sophistication and scale, this talk by Dmitrijs Trizna from Microsoft addresses the critical asymmetry currently favoring offensive actors in the cybersecurity landscape. Trizna, a seasoned expert with 15 years in infosec and a deep focus on AI for the past five, unpacks how threat actors are rapidly leveraging large language models (LLMs) and artificial intelligence to automate their operations, leading to an unprecedented surge in vulnerabilities and supply chain attacks. The core premise is that traditional, human-centric vulnerability management approaches are no longer scalable or effective against this evolving threat.
AI review
Competent practitioner talk from someone doing real work at Microsoft, with genuine operational grounding in AI-assisted vuln triage. The core insights — context engineering matters more than agent complexity, LLMs are bad scrapers but good aggregators — are sound, but they're not novel to anyone who's actually built these systems. BSides NYC appropriate, not Black Hat headliner material.