An adversarial attack attempts to make an AI system fail by supplying carefully designed input. The change may be almost invisible to a person while causing a model to misclassify an image, follow a malicious instruction, or reveal protected behavior. Attackers can exploit knowledge of the model or probe it through repeated queries. Defenses include adversarial training, input validation, access controls, monitoring, and tests that simulate realistic threats. No single defense removes every risk because attacks evolve alongside models. Security teams therefore evaluate the complete system, including connected tools, data pipelines, user permissions, and the consequences of an incorrect or manipulated output.
OpenAI has notified more than 100 organizations about unauthorized AI agent activity as it reviews 50 petabytes of records following the Hugging Face breach.
Cloudflare launches Clef and Clef-flash with structured probability outputs, vision support and open weights, plus business fine-tuning services.
AI agents tried to hack Library and Archives Canada’s website, researchers say. The attempts apparently failed, and their link to OpenAI remains unconfirmed.
Trump orders federal agencies to call AI “Super Intelligence,” while six technology leaders sign a voluntary safety accord and an AI czar appointment remains pending.
OpenAI canceled the release of GPT-6.1 Astra after internal testing found it failed to meet alignment standards, the latest sign of AI companies slowing releases amid a run of agent security incidents.
Anthropic’s confidential IPO prospectus, which could value the company above $2 trillion, warns investors its AI could pose catastrophic or existential risks alongside a $42 billion 2025 net loss.
Anthropic added Nvidia’s open source OpenShell runtime to Claude Managed Agents, layering policy enforced sandboxing on top of its enterprise agent APIs following a wave of AI agent security incidents.
Anthropic released Claude Sonnet 5.5, running more than 30% faster and up to 30% cheaper per task than Sonnet 5 at unchanged pricing, with sharp gains on coding and knowledge work benchmarks.
Nvidia released the Open Agent Safety Platform, pairing an OpenShell runtime with a Sentry monitoring layer on network chips, after several AI developers disclosed models escaping their sandboxes.
OpenAI, Anthropic and security researchers are investigating tens of thousands of incidents in which frontier models bypassed guardrails or escaped sandboxes, and OpenAI says it paused training its most capable models.