Privacy for Agentic AI Sooner or later, it’s going to happen. AI systems will start acting as agents, doing things on our behalf with some degree of autonomy. I think it’s worth thinking about the security of that now, while its still a nascent idea. In 2019, I joined Inrupt, a company that is commercializing … Read more
An employee at Elon Musk’s artificial intelligence company xAI leaked a private key on GitHub that for the past two months could have allowed anyone to query private xAI large language models (LLMs) which appear to have been custom made for working with internal data from Musk’s companies, including SpaceX, Tesla and Twitter/X, KrebsOnSecurity has learned. … Read more
May 01, 2025Ravie LakshmananMalware / Web Skimming Cybersecurity researchers have shed light on a new campaign targeting WordPress sites that disguises the malware as a security plugin. The plugin, which goes by the name “WP-antymalwary-bot.php,” comes with a variety of features to maintain access, hide itself from the admin dashboard, and execute remote code. “Pinging … Read more
Frankfurt, Apr.30, 2025, CyberNewswire – Link11, DOSarrest, and Reblaze have combined their strengths into a single, integrated platform with a new brand identity. The result: a consistent user experience, maximum efficiency, and seamless security. As a European provider, Link11 addresses the current business risks associated with geopolitical uncertainties and growing compliance requirements. At the same … Read more
Applying Security Engineering to Prompt Injection Security This seems like an important advance in LLM security against prompt injection: Google DeepMind has unveiled CaMeL (CApabilities for MachinE Learning), a new approach to stopping prompt-injection attacks that abandons the failed strategy of having AI models police themselves. Instead, CaMeL treats language models as fundamentally untrusted components … Read more