DYNASHIELD: A Black-Box Moving Target Defense for LLMs via Dynamic Decoding Customization
Read the original on arXiv Computation and Language →The paper introduces DYNASHIELD, a black-box moving target defense for large language models that dynamically customizes decoding hyperparameters and system prompts during inference. It first identifies decoding configurations that lower the probability of successful jailbreak attacks, then samples from a weighted pool of these configurations to add controlled variability to the model’s behavior. Experiments on seven open-source LLMs and four state-of-the-art jailbreak attacks show that DYNASHIELD significantly reduces attack success rates while preserving response quality and adding minimal inference overhead.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.