PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
Train-time data poisoning attacks threaten machine learning models by introducing adversarial examples during training, leading to misclassification. Current defense methods often reduce generalization performance, are attack-specific, and impose significant training overhead. To address this, we introduce a set of universal data purification methods using a stochastic transform, $\Psi(x)$, realized via iterative Langevin dynamics of Energy-Based Models (EBMs), Denoising Diffusion Probabilistic Models (DDPMs), or both. These approaches purify poisoned data with minimal impact on classifier generalization. Our specially trained EBMs and DDPMs provide state-of-the-art defense against various attacks (including Narcissus, Bullseye Polytope, Gradient Matching) on CIFAR-10, Tiny-ImageNet, and CINIC-10, without needing attack or classifier-specific information. We discuss performance trade-offs and show that our methods remain highly effective even with poisoned or distributionally shifted generative model training data.
Code (1)
Tasks
Data PoisoningDenoisingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Models
Deep neural networks (DNNs) have risen to prominence as key solutions in numerous AI applications for earth observation (AI4EO). However, their susceptibility to adversarial examples poses a critical challenge, compromis…
Adversarial DefenseAdversarial PurificationDenoisingEarth Observation+2Universal Adversarial Purification with DDIM Metric Loss for Stable Diffusion
Stable Diffusion (SD) often produces degraded outputs when the training dataset contains adversarial noise. Adversarial purification offers a promising solution by removing adversarial noise from contaminated data. Howev…
PureEBM: Universal Poison Purification via Mid-Run Dynamics of Energy-Based Models
Data poisoning attacks pose a significant threat to the integrity of machine learning models by leading to misclassification of target distribution data by injecting adversarial examples during training. Existing state-o…
Data PoisoningFLARE: Toward Universal Dataset Purification against Backdoor Attacks
Deep neural networks (DNNs) are susceptible to backdoor attacks, where adversaries poison datasets with adversary-specified triggers to implant hidden backdoors, enabling malicious manipulation of model predictions. Data…
AllDecoupling Semantics and Fingerprints: A Universal Representation for AI-Generated Image Detection
Detecting AI-generated images across unseen architectures remains challenging, as existing models often overfit to generator-specific fingerprints and semantic content rather than learning universal forgery traces. We at…