Offense at Scale: How Frontier AI Lowers the Cost of Cyber Attacks - Irregular
Frontier AI is lowering the cost of vulnerability research and exploit development. When those bottlenecks compress, attacks scale and the defensive baseline shifts. Security leaders will need AI-assisted resilience to keep pace.
March 2, 2026 Executive Summary Frontier AI models are crossing capability thresholds in offensive security tasks. Our evaluations, along with results from other labs, show consistent, measurable improvement on the subtasks that make up real-world offensive workflows: vulnerability research, exploit development, and iterative probing of complex systems. These are the steps where specialist expertise has historically been the bottleneck, and that is starting to change. For years, the majority of defensive postures were built on an assumption we call attacker scarcity : that sophisticated offens
Explore this link on the map →related reading
- Emergent Cyber Behavior: When AI Agents Become Offensive Threat Actors - Irregularirregular.com
- FIRST Mid-Year Vulnerability Forecast Confirms Historic Surge, Projects ~66,000 CVEs in 2026first.org
- Security incident disclosure — July 2026huggingface.co
- Disrupting the first reported AI-orchestrated cyber espionage campaign \ Anthropicanthropic.com
- [2603.11214] Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenariosarxiv.org
- Cybersecurity Looks Like Proof of Work Nowdbreunig.com
- AI 2027ai-2027.com
- Project Glasswing: Securing critical software for the AI era \ Anthropicanthropic.com
- Autonomous hackingnoahlebovic.com
- My picture of the present in AI — LessWronglesswrong.com
- Off Target | CNAScnas.org
- Vulnerability Research Is Cooked - Quarrelsomesockpuppet.org