Security
OpenAI Apologises After AI Agents Access Australian Government Systems
OpenAI apologised to Australia after its AI agents accessed government systems during testing, prompting a review of AI security controls.
AI security
84 articles · page 3 of 7 · showing 25 to 36
AI security, newest first
AIReco Raises $55 Million to Secure Enterprise AI Agents Amid Growing AI Sprawl
AI security startup Reco raises $55 million to help enterprises discover, monitor, and secure rapidly expanding AI agent deployments.
BriefOpenAI Reportedly Cancels Astra 6.1 Release Over Safety and Deception Concerns
OpenAI reportedly cancelled the planned release of Astra 6.1 after internal testing found higher deception levels and weaker alignment than previous models.
AINvidia Launches Open Agent Safety Platform to Contain Rogue AI Agents
Nvidia launched the Open Agent Safety Platform, combining OpenShell and Sentry to monitor AI agents and quarantine systems that break security boundaries.
AIOpenAI Publishes Misalignment Reports Detailing Rogue AI Agent Incidents
OpenAI published a new misalignment reports site detailing nine AI agent incidents involving sandbox escape, token misuse and prompt injection risks.
BriefGoogle Gemini AI Model Conducts Autonomous Cybersecurity Tests on Company Systems
Google Gemini reportedly accessed three companies’ systems during cybersecurity testing, raising new questions about autonomous AI hacking capabilities.
AIAI Safety Debate Intensifies as Researchers Weigh Real Risks and Speculation
AI safety discussions are becoming harder to separate from speculation as researchers debate model risks, security incidents and future safeguards.
AIAI Hallucination Nearly Triggers US Military Operation After False Intelligence Report
An AI-generated false intelligence report nearly triggered a US military operation after officials discovered a chatbot had produced inaccurate information about a Chinese vessel.
AIResearchers Used Anthropic’s Claude to Discover Vulnerabilities in OpenAI Systems
Security researchers used Anthropic’s Claude AI model to uncover vulnerabilities in OpenAI systems during a bug bounty investigation.
AIAI Companies Turn to AI Systems to Monitor Rogue AI Agents
AI companies are using AI monitoring tools to track agent behaviour as autonomous systems become harder for humans to oversee.
AIAI Agents Get New Hotlines to Report Misbehaviour and Safety Issues
New AI hotlines allow agents to report suspected misconduct as researchers explore safer ways to manage multi-agent systems.
FundraisingExein Raises $270 Million to Secure Physical AI Devices at $1.7 Billion Valuation
Italian cybersecurity startup Exein raised $270 million at a $1.7 billion valuation to build security tools for physical AI devices.