Ai Security

Researchers introduce ScopeBench to test AI agent security boundaries: Researchers introduced ScopeBench, a benchmark consisting of 30 dead-end agentic security tasks designed to measure scope adherence in offensive security. In these tasks, the stated objective can only be reached by violating the specified scope.

AI Safety & Alignment • arXiv

New skill cascading attacks distribute malicious goals across AI agents: Researchers have introduced skill cascading attacks, a new threat paradigm targeting skill-based agent systems. The attack distributes a malicious objective across multiple skills so that each individual modification appears benign in isolation.

Security • arXiv

Red Queen Bio • Red Queen Bio

OpenAI-backed biosecurity startup Red Queen Bio raises $36M: AI biosecurity startup Red Queen Bio has raised $36 million in funding. The company, which is backed by OpenAI, uses artificial intelligence to design antibody drugs against novel pathogens. Its technology aims to defend against threats including future AI-enabled bioweapons.