Collaborate Disseminate
Distillation is an ‘attack’ against an AI model designed to capture outputs, understand reasoning processes, and subsequently train a different model.
The post US Agencies Warn China Is Systematically Extracting Frontier AI Capabilities appeared first … Continue reading US Agencies Warn China Is Systematically Extracting Frontier AI Capabilities
Attackers are using trusted Microsoft services and blob URLs to generate stealthy phishing pages that leave defenders with no static website to detect or block.
The post New Phishing Attack Creates Malicious Pages Inside the Victim’s Browser appeared f… Continue reading New Phishing Attack Creates Malicious Pages Inside the Victim’s Browser
Malicious prompts concealed in documents, metadata, emails, images and code can manipulate autonomous agents into taking dangerous actions.
The post The Hidden Instructions That Can Hijack AI Agents appeared first on SecurityWeek.
Continue reading The Hidden Instructions That Can Hijack AI Agents
OpenAI agents made 15,000–18,000 autonomous edits to a German wiki over three months, evading moderation and echoing tactics seen in the Hugging Face breach.
The post OpenAI Agents Hijack Another Victim Website appeared first on SecurityWeek.
Continue reading OpenAI Agents Hijack Another Victim Website
The Daybreak initiative will provide subsidized AI cyber capabilities, training and technical assistance, though OpenAI has disclosed few details about costs and eligibility.
The post OpenAI Pledges $1 Billion to Bring Frontier AI to Critical Infrastru… Continue reading OpenAI Pledges $1 Billion to Bring Frontier AI to Critical Infrastructure Defenders
Catch promises the capabilities of a trusted executive assistant, with built-in controls governing what data and systems it can access.
The post Catch Raises $5 Million for AI Executive Assistant With Guardrails appeared first on SecurityWeek.
Continue reading Catch Raises $5 Million for AI Executive Assistant With Guardrails
New models, trained using NVIDIA Nemotron 3 Ultra, aim to catch rogue agent behavior before it executes, without the latency of large-model review.
The post Capsule Security Launches ‘AI Circuit Breaker’ to Stop Rogue Agents appeared first … Continue reading Capsule Security Launches ‘AI Circuit Breaker’ to Stop Rogue Agents
The startup’s firewall evaluates AI skills, plugins and MCP servers for malicious instructions, excessive permissions and software supply chain risks.
The post AI Agent Firewall Startup AIR Security Emerges From Stealth With $50 Million appeared first … Continue reading AI Agent Firewall Startup AIR Security Emerges From Stealth With $50 Million
The security tool intercepts potentially dangerous agent actions, blocking clear threats and requesting human approval when intent is uncertain.
The post OpenLeash Adds a Human Check to Risky AI Agent Actions appeared first on SecurityWeek.
Continue reading OpenLeash Adds a Human Check to Risky AI Agent Actions
Late amendments to the Cyber Security and Resilience Bill would give ministers new powers to restrict risky technology providers as supply chain attacks intensify.
The post UK Moves to Block High-Risk Tech Suppliers From Critical Infrastructure appeare… Continue reading UK Moves to Block High-Risk Tech Suppliers From Critical Infrastructure