LLMSymGuard: A Symbolic Safety Guardrail Framework Leveraging Interpretable Jailbreak Concepts
This addresses safety vulnerabilities in LLMs for users and developers, offering a transparent defense mechanism, though it builds on existing interpretability methods.
The paper tackles the problem of jailbreaking attacks on large language models by introducing LLMSymGuard, a framework that uses sparse autoencoders to identify interpretable concepts related to jailbreak themes, enabling symbolic safety guardrails without fine-tuning.
Large Language Models have found success in a variety of applications; however, their safety remains a matter of concern due to the existence of various types of jailbreaking methods. Despite significant efforts, alignment and safety fine-tuning only provide a certain degree of robustness against jailbreak attacks that covertly mislead LLMs towards the generation of harmful content. This leaves them prone to a number of vulnerabilities, ranging from targeted misuse to accidental profiling of users. This work introduces \textbf{LLMSymGuard}, a novel framework that leverages Sparse Autoencoders (SAEs) to identify interpretable concepts within LLM internals associated with different jailbreak themes. By extracting semantically meaningful internal representations, LLMSymGuard enables building symbolic, logical safety guardrails -- offering transparent and robust defenses without sacrificing model capabilities or requiring further fine-tuning. Leveraging advances in mechanistic interpretability of LLMs, our approach demonstrates that LLMs learn human-interpretable concepts from jailbreaks, and provides a foundation for designing more interpretable and logical safeguard measures against attackers. Code will be released upon publication.