AINewsnow

Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery

This story is from 2026-09-10. It is preserved in the archive; the latest stories are on the live feed.

arXiv:2609.09647v1 Announce Type: new Abstract: Agentic systems are rapidly moving to production, where they read untrusted inputs, call tools with real permissions, and act autonomously, expanding the security surface beyond chat-only models. Yet standard evaluations remain single-turn and fail to…

Read the full story at arXiv cs.AI ↗

Timeline · 1 report

  1. 2026-09-10 04:00 · arXiv cs.AI
    Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery

More stories

  1. Trump announces a new 'AI Force,' but says he will not 'stifle' AI — Business Insider AI
  2. Introducing Kimi K3 on Amazon Bedrock — AWS Machine Learning Blog
  3. Introducing Amazon SageMaker HyperPod Inference Gateway — AWS Machine Learning Blog
  4. Introducing Astra for Law — OpenAI News
  5. Microsoft exec called AI scraping the “largest theft of labor in human history” — Ars Technica AI
  6. Newsom signs executive order to explore new AI rules, consider ‘kill switch’ — Politico Technology
  7. Google Joins OpenAI, Anthropic, Meta in Disclosing AI Hacks — Bloomberg AI
  8. Anthropic, OpenAI, SpaceXAI, Google sued over call to ‘pace’ AI development — Politico Technology

Get the daily brief of stories like this at 6:30 every morning →