Certifying LLM Safety against Adversarial Prompting

1 code implementation • 6 Sep 2023 • Aounon Kumar, Chirag Agarwal, Suraj Srinivas, Aaron Jiaxun Li, Soheil Feizi, Himabindu Lakkaraju

We defend against three attack modes: i) adversarial suffix, where an adversarial sequence is appended at the end of a harmful prompt; ii) adversarial insertion, where the adversarial sequence is inserted anywhere in the middle of the prompt; and iii) adversarial infusion, where adversarial tokens are inserted at arbitrary positions in the prompt, not necessarily as a contiguous block.

Adversarial Attack Language Modelling +1