AISI found AI agents taking unsanctioned online actions, including social engineering and code attacks, during controlled cyber tests. The UK’s AI…
Tag: AI Security
OpenAI Disrupts Poipet Scam Network Using ChatGPT Across Multiple Fraud Schemes
OpenAI said it disrupted a Cambodia-based scam operation that used its generative artificial intelligence (AI) chatbot ChatGPT to facilitate a wide range…
Poison Claude is Selling Cheap AI Tokens Built on Fake Accounts and Free Credits
A shadowy online service called Poison Claude is reselling access to Anthropic’s premium AI models at a significant discount. Researchers suggest that…
IBM’s agentic AI platform is under active attack – patch now
A critical Langflow flaw allowing RCE on default deployments is being exploited, says the CISA
Salt Security Launches Industry-First AWS WAF Managed Ruleset for AI Agents and API Protection
Salt Security has unveiled what it says is the industry’s first AWS WAF managed ruleset designed specifically to protect both APIs and AI agents,…
5 Best AI Detection & Response Platforms for 2026
Compare AI detection & response platforms for 2026, including Dash, Lakera, Operant AI, HiddenLayer and Prisma AIRS, for runtime threat protection and…
Paperclip AI Flaws Let Attackers Run Host Commands via Malicious Agent Imports
Two security flaws in Paperclip could let attackers execute commands on a network server or a developer’s computer. Paperclip is an open-source control…
White House walks tightrope on securing AI without stifling tech innovation
National Cyber Director Sean Cairncross said the administration wants to work collaboratively with the private sector.
“I’m Allowed”: Hackers Use Simple Claims to Bypass AI Guardrails
Cisco Talos found hackers using simple authorization claims to bypass AI guardrails, build DDoS attack tools, steal credentials and access live camera…
Stellar Cyber’s Auto-Triage AI matches human analysts 99.7% of the time
Stellar Cyber, the full-cycle AI-native security operations platform company, today released results from an independent study of 124 days of customer…
Paperclip AI Flaws Let Unauthenticated Attackers Run Commands
3 Paperclip flaws exposed data & allowed unauthenticated command execution in two deployment modes
Agentic AI Security: The Chatbot Era Is Already Over
There is a diagram most security teams still carry in their heads when they think about AI. A user talks to a chatbot. The chatbot talks to a large…
OpenAI Says AI Agent Breached Hugging Face During Cybersecurity Test
OpenAI has disclosed that one of its advanced artificial intelligence agents autonomously breached the boundaries of a controlled cybersecurity evaluation…
Shadow AI, Rogue Agents, and Data Leaks: A Special Report on Navigating AI Risk
Discover top enterprise AI risks — from shadow AI to rogue agents and data leaks — plus practical CISO strategies in the new Akamai SOTI special report.
ArmorCode enhances attack path analysis with new AI agents and Context Risk Graph
ArmorCode has announced a major expansion of its Agentic Control Plane. Four new Anya AI agents help security teams analyze cloud risks, assess…
AI Orchestration Framework Security Comparison
A new security evaluation of AI orchestration frameworks has revealed significant differences in how easily AI agents can be compromised based solely on…
Tenable broadens AI visibility across major LLMs and AI tools
Tenable has announced enhanced AI security capabilities within the Tenable One Exposure Management Platform. Tenable One AI Exposure now delivers expanded…
White House AI Security Strategy Avoids New Regulations
The White House has outlined its approach to artificial intelligence security through an executive order that deliberately avoids creating new regulatory…
INTERPOL flags AI as the new engine of African cybercrime
Africa’s growing digital economy is exposing governments, businesses and internet users to a rising wave of cybercrime. The continent recorded more than…
AI Agents Targeted Real People and Projects During Cybersecurity Tests
AI Security Institute reports Anthropic and OpenAI models going rogue against real people, organizations, and open source projects.