Using AI for Weapons Development
Using AI for Weapons Development Last week, Anthropic released a long and detailed document describing current misuses of their Claude...
AI
Anthropic CEO Calls for an AI Slowdown. Is It Possible?
Anthropic CEO Calls for an AI Slowdown. Is It Possible? Pierluigi Paganini September 14, 2026 Anthropic CEO calls for AI...
Microsoft’s Patching
Microsoft’s Patching Once a month, Microsoft pushes a security update to all Windows users. Tomorrow’s is a new record: Microsoft’s...
Security Affairs newsletter Round 594 by Pierluigi Paganini – INTERNATIONAL EDITION
Security Affairs newsletter Round 594 by Pierluigi Paganini – INTERNATIONAL EDITION Pierluigi Paganini September 13, 2026 A new round of...
My Talk at DEF CON
My Talk at DEF CON Last month, I gave a talk at DEF CON on AI hacking: what happens when...
The AI Supply Chain Has a Security Problem, and Much of It Is Sitting on the Open Internet
The AI Supply Chain Has a Security Problem, and Much of It Is Sitting on the Open Internet Pierluigi Paganini...
Cybersecurity in the Era of AI: What CISOs Actually Need to Get Right
Published: 10 September 2026 On 12 September I’m on stage in Karachi at the World CIO 200 Summit, Pakistan Edition,...
More Capable AI, Not Enough Guardrails
More Capable AI, Not Enough Guardrails Pierluigi Paganini September 10, 2026 AI agents are gaining real-world access faster than safeguards...
A New Claude ‘s Sandbox Failure Shows How AI Can Rationalize Real-World Harm
A New Claude ‘s Sandbox Failure Shows How AI Can Rationalize Real-World Harm Pierluigi Paganini September 10, 2026 Claude models...
AIs Compress Exploit Timeline
AIs Compress Exploit Timeline Give an AI agent a mere rumor of an exploit, and it’s enough for them to...
Proofpoint report flags resourcing gap as Australian CISOs take on AI risk
Australian chief information security officers are increasingly being asked to manage artificial intelligence-related cyber risks without additional resources, according to...
US Agencies Warn Chinese AI Firms Are Extracting Advanced AI Models
US Agencies Warn Chinese AI Firms Are Extracting Advanced AI Models Pierluigi Paganini September 09, 2026 US agencies accuse six...
Claude Fable Solves a Historical Cipher
Claude Fable Solves a Historical Cipher Claude Fable 5.1 solved a 370-year-old cipher in forty-four minutes. This tracks with what...
AIs as Modern Genies
AIs as Modern Genies This essay was written with Barath Raghavan, and originally appeared in Lawfare. In April, an artificial...
Stealing AI Reasoning Traces
Stealing AI Reasoning Traces Interesting research: “Stealing Reasoning Traces from Proprietary LLM APIs“: Abstract: Leading large language model providers now...
