UK researcher backdoors an open AI model for under £75
Manchester Metropolitan's Katie Paxton-Fear implanted a backdoor in an open-weight model in about an hour for under £75 ($100), using ten training examples.
Tag: AI Security
19 articles tagged AI Security
McKinsey's internal AI chatbot breached via basic SQL injection
Security firm CodeWall used an autonomous AI penetration tool to access McKinsey's Lilli chatbot, exposing 46.5 million chat messages and system configurations.
OpenClaw Security Fears Lead Meta and Other Firms to Restrict Use
Tech companies including Meta are banning the open-source agentic AI tool OpenClaw from company hardware over security and privacy concerns, despite its growing popularity among developers.
European Parliament Disables AI Features on Lawmakers' Devices
The European Parliament has switched off AI tools on official devices after its IT department could not guarantee where data was being sent.
Researchers Find 40,000 Exposed OpenClaw Instances on Public Internet
SecurityScorecard found over 40,000 exposed OpenClaw instances, with 63% of deployments vulnerable and nearly 13,000 exploitable via remote code execution.
UK Government Partners With Microsoft on Deepfake Detection Framework
The Home Office announces a new deepfake detection evaluation framework developed with Microsoft, aiming to set industry standards as deepfake volumes surge.
Researchers Warn Open-Source AI Models Vulnerable to Criminal Misuse
Joint SentinelOne and Censys research reveals thousands of open-source LLM deployments operating without guardrails, creating security risks for spam, phishing and disinformation.
Starling launches AI tool for scam monitoring
UK challenger bank Starling debuts its first AI-powered tool to identify purchase scams through image analysis with Google Cloud partnership.