Indirect Prompt Injection on Bing Chat (via) “If allowed by the user, Bing Chat can see currently open websites. We show that an attacker can plant an injection in a website the user is visiting, which silently turns Bing Chat into a Social Engineer who seeks out and exfiltrates personal information.” This is a really clever attack against the Bing + Edge browser integration. Having language model chatbots consume arbitrary text from untrusted sources is a huge recipe for trouble.
Recent articles
- New audio models from OpenAI, but how much can we rely on them? - 20th March 2025
- Calling a wrap on my weeknotes - 20th March 2025
- Not all AI-assisted programming is vibe coding (but vibe coding rocks) - 19th March 2025