Affected Vendor(s)
Affected Product(s)
Summary
Protect AI offer two Prompt Injection and Jailbreak classifiers on HuggingFace. These classifiers are heavily used by a range of guardrail systems and are designed to enable developers of AI applications to detect and react to incoming prompt injections and jailbreaks. We successfully demonstrated how an attacker can fully evade, or greatly degrade, classification accuracy of the classifier, enabling prompt injections and jailbreaks to pass through filters and subsequently to the protected AI application.
Timeline
Credit
Blog Post
References
Take the first step towards securing your AI. Book a demo now and we'll reach out to you.
