Evasion attacks, adversarial examples, and physical-world perturbations against computer vision, NLP, and autonomous systems. Mapped to MITRE ATLAS AML.T0043 and AML.T0015.
Activation steering — the technique of directly manipulating LLM internal representations mid-inference to alter model behaviour — is becoming more accessible to non-lab engineers via local models …
Google's Threat Intelligence Group (GTIG) has identified, for the first time, a criminal threat actor using a zero-day exploit believed to have been AI-generated, intended for mass exploitation before …
Research highlighted by Bruce Schneier confirms that LLMs are highly effective at embedding hidden messages within seemingly normal text, a technique known as text-in-text steganography. This …
Cisco's AI Threat Intelligence team has demonstrated that bounded pixel-level perturbations can recover the attack effectiveness of degraded typographic images against vision-language models (VLMs), …
Joey Melo, Principal Security Researcher at CrowdStrike, outlines his methodology for AI red teaming, focusing on manipulating LLM guardrails through jailbreaking and data poisoning without altering …
Google Threat Intelligence Group's Q4 2025 AI Threat Tracker documents a meaningful escalation in adversarial AI misuse, including a surge in model extraction (distillation) attacks, nation-state …
Microsoft's Security Blog outlines how AI is accelerating the offensive threat landscape, with models now capable of autonomously discovering vulnerabilities and chaining lower-severity issues into …
Artemis, a cybersecurity startup focused on AI-powered threat defence, has emerged from stealth with $70 million in funding, positioning itself to counter AI-driven attacks across applications, users, …
The article argues that AI's primary security risk lies not in introducing entirely new vulnerability classes, but in dramatically amplifying the impact and exploitability of well-established ones. …
A large-scale ad fraud and scareware campaign dubbed 'Pushpaganda' has been uncovered exploiting Google Discover by using AI-generated content to poison search discovery surfaces and lure users into …
Researchers at UC Berkeley demonstrated that every major AI agent benchmark — including SWE-bench, WebArena, OSWorld, and others — can be fully exploited to achieve near-perfect scores without solving …