While the shortest distance between two points is a straight line, a straight-line attack on a large language model isn't always the most efficient — and least noisy — way to get the LLM to do bad ...

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

Happy Groundhog Day! Security researchers at Radware say they've identified several vulnerabilities in OpenAI's ChatGPT ...

Security researchers from Radware have demonstrated techniques to exploit ChatGPT connections to third-party apps to turn ...

That's according to researchers from Radware, who have created a new exploit chain it calls "ZombieAgent," which demonstrates ...

Network defenders must start treating AI integrations as active threat surfaces, experts have warned after revealing three new vulnerabilities in Google Gemini. Tenable dubbed its latest discovery the ...

OpenAI develops automated attacker system to test ChatGPT Atlas browser security against prompt injection threats and ...

Security researchers have discovered a new indirect prompt injection vulnerability that tricks AI browsers into performing malicious actions. Cato Networks claimed that “HashJack” is the first ...

A now patched flaw in Microsoft 365 Copilot let attackers turn its diagram tool, Mermaid, into a data exfiltration channel–fetching and encoding emails through hidden instructions in Office documents.

OpenAI unveiled its Atlas AI browser this week, and it’s already catching heat. Cybersecurity researchers are particularly alarmed by its integrated “agent mode,” currently limited to paying ...

New findings from a group of researchers at the Black Hat hacker conference in Las Vegas has revealed that it only takes one "poisoned" document to gain access to private data using ChatGPT that has ...

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