Researchers found an indirect prompt injection flaw in Google Gemini that bypassed Calendar privacy controls and exposed ...

AI agents are rapidly moving from experimental tools to trusted decision-makers inside the enterprise—but security has not ...

CrowdStrike's 2025 data shows attackers breach AI systems in 51 seconds. Field CISOs reveal how inference security platforms ...

There’s a well-worn pattern in the development of AI chatbots. Researchers discover a vulnerability and exploit it to do ...

A massive security breach recently forced Ubisoft to take Rainbow Six Siege servers offline after a multi-group hack compromised internal systems. Attackers flooded player accounts with billions in ...

With the growing reliance on web applications and digital platforms, the use of application programming interfaces (APIs) has become increasingly popular. If you aren't familiar with the term, APIs ...

When you think of cyberattacks that compromise your account security, maybe you envisage Microsoft zero-day vulnerabilities being exploited in your software, or perhaps a hacker using ...

Cybersecurity news this week was largely grim. On the bright side, you still have one week remaining to claim up to $7,500 from AT&T’s $177 million data breach settlement! I've been writing and ...

Researchers from MIT, Northeastern University, and Meta recently released a paper suggesting that large language models (LLMs) similar to those that power ChatGPT may sometimes prioritize sentence ...

North Korean hacking group Lazarus is suspected of being behind an exploit that saw 45 billion won (about $30 million) drained from South Korea’s largest crypto exchange Upbit on Thursday, Yonhap News ...

OpenAI is notifying some ChatGPT API customers that limited identifying information was exposed following a breach at its third-party analytics provider Mixpanel. Mixpanel offers event analytics that ...

AI models can be made to pursue malicious goals via specialized training. Teaching AI models about reward hacking can lead to other bad actions. A deeper problem may be the issue of AI personas.