Offensive AI
AI in the attacker’s hands, and in the defender’s. AI-assisted intrusion, automated vulnerability discovery, malware, social engineering and deepfake fraud, alongside the defensive tooling built to answer them.
-
A Guardrail Checks a Request. An Attacker Runs an Operation.
Three campaigns since late 2025 have got AI agents to run offensive work. None needed an adversarial prompt. Two lied…
Read More » -
Your Incident Response Plan Assumes a Model That Will Answer
Hugging Face's responders were refused by commercial models when they tried to analyse their own attack logs, and finished the…
Read More » -
AI: The Shifting Battlefield in the Cybersecurity Arms Race
Cybersecurity strategies need to change in order to address the new issues that Machine Learning (ML) and Artificial Intelligence (AI)…
Read More »
