English

MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs

Cryptography and Security 2026-02-24 v1 Artificial Intelligence Computation and Language Machine Learning

Abstract

Defending LLMs against adversarial jailbreak attacks remains an open challenge. Existing defenses rely on binary classifiers that fail when adversarial input falls outside the learned decision boundary, and repeated fine-tuning is computationally expensive while potentially degrading model capabilities. We propose MANATEE, an inference-time defense that uses density estimation over a benign representation manifold. MANATEE learns the score function of benign hidden states and uses diffusion to project anomalous representations toward safe regions--requiring no harmful training data and no architectural modifications. Experiments across Mistral-7B-Instruct, Llama-3.1-8B-Instruct, and Gemma-2-9B-it demonstrate that MANATEE reduce Attack Success Rate by up to 100\% on certain datasets, while preserving model utility on benign inputs.

Keywords

Cite

@article{arxiv.2602.18782,
  title  = {MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs},
  author = {Chun Yan Ryan Kan and Tommy Tran and Vedant Yadav and Ava Cai and Kevin Zhu and Ruizhe Li and Maheep Chaudhary},
  journal= {arXiv preprint arXiv:2602.18782},
  year   = {2026}
}
R2 v1 2026-07-01T10:45:34.361Z