Google’s new frontier model scored 88.2% on SEC-bench Pro and is rolling out first to vetted cyber defenders via its Fairwind Program.

The post Google Touts Powerful Cybersecurity Capabilities in Gemini 4 Carbon Model appeared first on SecurityWeek.

Cisco open sourced Project Quarry, a rule language for detecting AI agent attacks that only emerge across sequences of benign actions.

The post Cisco Open Sources Quarry to Catch AI Agent Attacks Hidden in Harmless Steps appeared first on SecurityWeek.

Anthropic presents its own initial public offering as a step toward mitigating the risks it believes AI poses.

The post Risks Spelled Out for Anthropic Investors Include Possible Harms From Runaway AI appeared first on SecurityWeek.

A string of hacking incidents by rogue AI agents also has raised fears the technology will slip free of human control to carry out harmful, life-threatening tasks.

The post Anthropic Files for Potentially the Biggest IPO Ever as CEO Warns of Risk to Humanity From AI appeared first on SecurityWeek.

Xint says a flaw in OpenAI’s compaction process let researchers move reasoning traces between models, potentially making it cheaper to distill a rival AI.

The post Stolen AI Reasoning Could Help China Build Cheaper Rivals appeared first on SecurityWeek.

The model engaged in severe overreach and dishonesty, creating fake identities and submitting malicious code on GitHub.

The post Mythos 5 Ignored Real-World Harm in July Attack appeared first on SecurityWeek.

The state-sponsored hackers targeted hundreds of organizations and gained privileged access to some environments.

The post China APT Uses AI Pentest Tool Artex in ConnectWise Attacks appeared first on SecurityWeek.

Hackers used compromised GitHub CLI OAuth tokens to push and approve malicious packages on PyPI and Docker.

The post LiteLLM Compromised in Fresh Supply Chain Attack appeared first on SecurityWeek.

Deceptive prompts lure AI agents into decoys and dead ends, cutting attack success by up to 91% in tests and raising the cost of a successful attack 23-fold.

The post ‘Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake Targets appeared first on SecurityWeek.

Rapid7’s Q3 analysis finds high-severity flaws exploited within three days on average, while AI appeared in just 8% of tracked incidents.

The post High-Severity Flaws Exploited in Three Days as Ransomware Dominates Q3: Rapid7 appeared first on SecurityWeek.

In two internal incidents, agents read routine coding instructions as permission to weaken monitoring, and one gave a false answer about it.

The post OpenAI Agents Silenced Security Team Alerts, Removed Misalignment Monitor appeared first on SecurityWeek.

The DHS said agencies should remove DeepSeek products as well as third-party products and services developed using DeepSeek from their IT systems.

The post China Defends DeepSeek After US Ban of Its AI From Government Systems appeared first on SecurityWeek.

Tasked with writing an application for a US defense contractor, the model made the code 19% more likely to be hackable.

The post Chinese AI Model Writes More Hackable Code When Told It’s for US Contractor appeared first on SecurityWeek.

NIST, CISA and NSA share ten voluntary practices for preparing for, detecting, responding to, recovering from, and reporting rogue AI agent incidents.

The post US Agencies Detail Incident Response Practices for Rogue AI Agents appeared first on SecurityWeek.

Where your developers sit on the AI adoption scale has a real impact on how you are addressing security risk.

The post The Key to AI Software Security Isn’t Speed, It’s Maturity appeared first on SecurityWeek.

At least three threat actors have been abusing Cairn for persistent access and financial theft.

The post AI Platform Cairn Abused to Hack Over 100 Organizations appeared first on SecurityWeek.

Abdulrahman Alfozan’s wife and young son also left the country the day after the 35-year-old Saudi national’s arrest.

The post Ex-OpenAI Worker Accused of Bugging Conference Room Planned to Fly to Saudi Arabia, Prosecutors Say appeared first on SecurityWeek.

Microsoft says companies should treat AI agents as insiders, and is adding controls that grant access per task and tighten it as an agent’s risk rises.

The post Microsoft Targets Rogue AI Agents With Dynamic Permissions, Risk Scoring appeared first on SecurityWeek.

Opaque Systems has developed technology that lets AI systems use sensitive data while keeping it protected by the underlying hardware.

The post Anthropic Acquires Confidential AI Startup Opaque Systems appeared first on SecurityWeek.

The Takedown of an Underground Phishing Engine A coordinated operation led by Microsoft’s Digital Crimes Unit, Health-ISAC, and international law enforcement recently dismantled a massive Chinese-language phishing marketplace responsible for...

The post International Law Enforcement Dismantles Multimillion-Dollar Phishing Network appeared first on Cyber Defense Magazine.