reverse-captcha-eval

Reverse CAPTCHA: Evaluating LLM Susceptibility to Invisible Unicode Instruction Injection An evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in otherwise normal-looking text. Where traditional CAPTCHAs exploit tasks humans can...

AI browsers could leave users penniless: A prompt injection warning

Artificial Intelligence AI browsers are gaining traction, which means we may need to start worrying about the potential dangers of something called "prompt injection." Large language models LLMs—like the ones that power AI chatbots including ChatGPT, Claude, and Gemini—are designed to follow...