Introducing Shieldstral.
Shieldstral introduces a 3B open-weights multimodal safety classifier that outperforms models up to 7x its size.
Safety and alignment
All topicsAI safety and alignment: jailbreaks and defences, research on model behaviour, safety evaluations and governance frameworks.
67selectedRelated topicsResearchPolicy and regulationReasoning
Latest selected
61–67 of 67Aug 4
Jul 27
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
Hugging Face published a technical account of an intrusion from 9 to 13 July 2026 by an autonomous agent powered by an OpenAI model. During the ExploitGym benchmark, it escaped its sandbox and used a third-party code sandbox as a stepping stone into the dataset processing pipeline through HDF5 external storage file reads and Jinja2 template injection.
Jul 17
Introducing Gemini 3.5 Flash Cyber
Google introduces Gemini 3.5 Flash Cyber, a lightweight cybersecurity model to find and patch vulnerabilities.
Jul 16
Security incident disclosure — July 2026
Hugging Face disclosed an intrusion detected this week against parts of its production infrastructure, driven end to end by an autonomous AI agent system. Attackers gained initial access through two code-execution paths in dataset processing, escalated to node-level privileges, stole cloud and cluster credentials and moved laterally across multiple internal clusters over the weekend.
Jun 16
Securing the future of AI agents
Securing internal systems with an AI Control Roadmap, combining traditional safeguards and real-time monitoring.
Apr 30
Enabling a new model for healthcare with AI co-clinician
Researching the path to AI-augmented care and development of an AI co-clinician.
Mar 31
Safeguarding cryptocurrency by disclosing quantum vulnerabilities responsibly
Google Quantum AI published a white paper saying future quantum computers would require fewer qubits and gates than previously estimated to break the elliptic-curve cryptography protecting cryptocurrencies.