ChatGPT falls to new data-pilfering attack as a vicious cycle in AI continues

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

Radware Unveils “ZombieAgent”: A Newly Discovered Zero-Click, AI Agent Vulnerability Enabling Silent Takeover and Cloud-Based Data Exfiltration

Radware ® (NASDAQ: RDWR), a global leader in application security and delivery solutions for multi-cloud environments, today announced the discovery of ZombieAgent, a new zero-click indirect prompt ...
Dark Reading

ChatGPT's Memory Feature Supercharges Prompt Injection

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

OpenAI putting bandaids on bandaids as prompt injection problems keep festering

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

Radware's H1 threat report: 500% spike in malicious web transactions

MAHWAH, N.J. Aug. 24, 2023—Radware, a leading provider of cyber security and application delivery solutions, released its First Half 2023 Global Threat Analysis Report. The comprehensive report ...