Uber's Agentic AI Detection and Response system correlates LLM reasoning with MCP tool calls to catch prompt injection, credential leaks, and rogue agent behavior across thousands of production coding sessions.
Uber's Agentic AI Detection and Response system correlates LLM reasoning with MCP tool calls to catch prompt injection, credential leaks, and rogue agent behavior across thousands of production coding sessions.
Researchers from HKUST and NUS propose a tagging-and-filtering defense that asks LLMs to cite which instruction they are answering, cutting prompt injection success rates from over 80% to under 1% without any fine-tuning.
Researchers from Clemson, Wayne State, and UW have published ADSD, the first prompt-suffix attack to collapse verifier acceptance in speculative decoding, inflating inference time by 62% on math benchmarks and over 140% on code tasks while leaving output quality intact.
Researchers presenting at ICML 2026 have demonstrated that LLMs identify text roles by writing style rather than structure, making it impossible to fully prevent attackers from injecting spoofed reasoning into model chains — affecting GPT-5, Claude, and every other major frontier model.
Production LLM applications routinely embed confidential business logic, persona instructions, and API call patterns inside system prompts. Attackers have developed a reliable toolkit for extracting that content -- and most deployments have no controls against it.
A June 2026 arxiv paper demonstrates that model extraction attacks have a detectable semantic signature in API traffic — and that simple statistical detection outperforms complex filtering approaches.
AI agents generate a new class of security event that existing SIEM infrastructure was not designed to process. DeepMind's June 2026 control roadmap, OWASP's Agentic Top 10, and the EU AI Act's August logging deadline all converge on the same problem: security teams cannot monitor what they are not capturing.
Three papers published in 2026 confirm what practitioners suspected: LLM safety alignment is structurally shallow, and fine-tuning APIs are the widest open bypass.