Tenet Security's DEF CON August 2026 research expands Agentjacking to Cloudflare, Datadog, and Sentry — 90% success rate, 15,000+ organisations exposed, DNS hijacking via AI coding agent manipulation, zero traditional exploitation required.
Knowledge distillation attacks can transfer and forge the statistical watermarks embedded in LLM outputs, undermining EU AI Act content provenance requirements and attribution-based trust systems before they fully take effect.
A paper accepted at ICML 2026 shows LLMs infer speaker role from text style, not role tags — enabling a zero-shot attack called CoT Forgery that achieves 60% success against frontier models by injecting fabricated reasoning.
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.