Plentiful Jailbreaks with String Compositions

Large language models (LLMs) remain vulnerable to a slew of adversarial attacks and jailbreaking methods. One common approach employed by white-hat attackers, or \textit{red-teamers}, is to process model inputs and outputs using string-level obfuscations, which can include leetspeak, rotary ciphers, Base64, ASCII, and more. Our work extends these encoding-based attacks by unifying them in a framework of invertible string transformations. With invertibility, we can devise arbitrary \textit{string compositions}, defined as sequences of transformations, that we can encode and decode end-to-end programmatically. We devise a automated best-of-n attack that samples from a combinatorially large number of string compositions. Our jailbreaks obtain competitive attack success rates on several leading frontier models when evaluated on HarmBench, highlighting that encoding-based attacks remain a persistent vulnerability even in advanced LLMs.

Endless Jailbreaks with Bijection Learning

Despite extensive safety training, LLMs are vulnerable to adversarial inputs. In this work, we introduce a simple but powerful attack paradigm, bijection learning, that yields a practically endless set of jailbreak prompts. We exploit language models' advanced reasoning capabilities to teach them invertible languages (bijections) in context, pass encoded queries to the model to bypass built-in safety mechanisms, and finally decode responses back into English, yielding helpful replies to harmful requests. Our approach proves effective on a wide range of frontier language models and harm categories. Bijection learning is an automated and universal attack that grows stronger with scale: larger models with more advanced reasoning capabilities are more susceptible to bijection learning jailbreaks despite stronger safety mechanisms.