MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Density EstimationSimilar Papers 제목 키워드 기반
Counting Manatee Aggregations using Deep Neural Networks and Anisotropic Gaussian Kernel
Manatees are aquatic mammals with voracious appetites. They rely on sea grass as the main food source, and often spend up to eight hours a day grazing. They move slow and frequently stay in group (i.e. aggregations) in s…
Crowd CountingScene RecognitionSchedulingDetection of manatee vocalisations using the Audio Spectrogram Transformer
The Antillean manatee (\emph{Trichechus manatus}) is an endangered herbivorous aquatic mammal whose role as an ecological balancer and umbrella species underscores the importance of its conservation. An innovative approa…
DenoisingTransfer LearningThe Safety-Aware Denoiser for Text Diffusion Models
Recent work on text diffusion models offers a promising alternative to autoregressive generation, but controlling their safety remains underexplored. Existing safety approaches are geared toward autoregressive models and…
Long Tail Image Generation Through Feature Space Augmentation and Iterated Learning
Image and multimodal machine learning tasks are very challenging to solve in the case of poorly distributed data. In particular, data availability and privacy restrictions exacerbate these hurdles in the medical domain. …
Image AugmentationImage GenerationRapid and Safe Trajectory Planning over Diverse Scenes through Diffusion Composition
Safe trajectory planning in complex environments must balance stringent collision avoidance with real-time efficiency, which is a long-standing challenge in robotics. In this work, we present a diffusion-based trajectory…
Collision AvoidanceTrajectory Planning