Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with content, and download exclusive resources. Dany Lepage discusses the architectural ...
When security researcher Johann Rehberger recently reported a vulnerability in ChatGPT that allowed attackers to store false information and malicious instructions in a user’s long-term memory ...
ChatGPT Atlas,' released by OpenAI in October 2025, incorporates an AI agent that can perform tasks such as information gathering and email processing. To strengthen the security of ChatGPT Atlas, ...
OpenAI's new AI browser, Atlas, faces immediate security concerns. Experts warn its ability to act on the internet could make it a potent attack tool, with hackers potentially stealing sensitive data ...
Exclusive: Guardian testing reveals AI-powered search tools can return false or malicious results if webpages contain hidden text The Guardian’s journalism is independent. We will earn a commission if ...
Some of the latest, best features of ChatGPT can be twisted to make indirect prompt injection (IPI) attacks more severe than they ever were before. That's according to researchers from Radware, who ...
Would you trust an AI chatbot like ChatGPT or Gemini with your emails, financial data, or even browsing habits and data? Most of us would probably answer no to that question, and yet that’s exactly ...
In the nascent field of AI hacking, indirect prompt injection has become a basic building block for inducing chatbots to exfiltrate sensitive data or perform other malicious actions. Developers of ...
The New York Times, a major American newspaper company, is suing OpenAI and Microsoft for using New York Times content to train ChatGPT and other AI systems. In response, OpenAI claimed that 'The New ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results