Academic and industry research shaping the future of AI security, attack, and defence.
NDSS 2026 research shows LLMs can be systematically tricked into missing deliberately planted vulnerabilities through Familiar Pattern Attacks — automated, black-box exploits of the abstraction bias that affects every major model family.
University of Toronto researchers presented GPUBreach at Black Hat 2026 — a Rowhammer attack that escalates from an unprivileged CUDA kernel to a host root shell, bypassing IOMMU, threatening shared AI cloud GPU infrastructure.
A timing side channel in global KV-cache sharing lets unprivileged tenants reconstruct other users' prompts, PII, and system instructions from vLLM, SGLang, and similar inference frameworks. Multiple CVEs have been assigned; patches are in progress.
Researchers found that encrypted chain-of-thought blocks returned by OpenAI, Anthropic, and Google's reasoning APIs used a shared global key, letting weaker models decode stronger models' hidden reasoning and exposing 704 real privacy artifacts in published developer logs.
VulnCheck's State of Exploitation 1H-2026 report quantifies AI-attributed vulnerability discovery for the first time. The headline finding is counterintuitive: AI-found bugs are exploited at roughly the same rate as everything else in the CVE catalogue.