paper-with-me

Papers

BadRSSD: Backdoor Attacks on Regularized Self-Supervised Diffusion Models

2026-03-01 · Jiayao Wang, Yiping Zhang, Mohammad Maruf Hasan, Xiaoying Lei, Jiale Zhang, Junwu Zhu, Qilin Wu, Dongfang Zhao arxiv

Self-supervised diffusion models learn high-quality visual representations via latent space denoising. However, their representation layer poses a distinct threat: unlike traditional attacks targeting generative outputs, its unconstrained latent semantic space allows for stealthy backdoors, permitting malicious control upon triggering. In this paper, we propose BadRSSD, the first backdoor attack targeting the representation layer of self-supervised diffusion models. Specifically, it hijacks the semantic representations of poisoned samples with triggers in Principal Component Analysis (PCA) space toward those of a target image, then controls the denoising trajectory during diffusion by applying coordinated constraints across latent, pixel, and feature distribution spaces to steer the model toward generating the specified target. Additionally, we integrate representation dispersion regularization into the constraint framework to maintain feature space uniformity, significantly enhancing attack stealth. This approach preserves normal model functionality (high utility) while achieving precise target generation upon trigger activation (high specificity). Experiments on multiple benchmark datasets demonstrate that BadRSSD substantially outperforms existing attacks in both FID and MSE metrics, reliably establishing backdoors across different architectures and configurations, and effectively resisting state-of-the-art backdoor defenses.

📄 PDF Abstract BibTeX arXiv:2603.01019

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Seal Your Backdoor with Variational Defense

2025-03-11 · Ivan Sabolić, Matej Grcić, Siniša Šegvić

We propose VIBE, a model-agnostic framework that trains classifiers resilient to backdoor attacks. The key concept behind our approach is to treat malicious inputs and corrupted labels from the training dataset as observ…

Representation LearningVariational Inference

Towards Imperceptible Backdoor Attack in Self-supervised Learning

2024-05-23 · Hanrong Zhang, Zhenting Wang, Tingxu Han, Mingyu Jin 외

Self-supervised learning models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in self-supervised learning often involve noticeable triggers, like colored patches, which are vulnerable t…

Backdoor AttackSelf-Supervised Learning

An Embarrassingly Simple Backdoor Attack on Self-supervised Learning

2022-10-13 · ICCV 2023 1 · Changjiang Li, Ren Pang, Zhaohan Xi, Tianyu Du 외

As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels. In addition to eliminating the need for labeled data, r…

Adversarial RobustnessBackdoor AttackSelf-Supervised Learning

Backdoor Attacks on Self-Supervised Learning

2021-05-21 · CVPR 2022 1 · Aniruddha Saha, Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Hamed Pirsiavash

Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., …

Backdoor AttackInductive BiasKnowledge DistillationSelf-Supervised Learning

Towards Understanding How Self-training Tolerates Data Backdoor Poisoning

2023-01-20 · Soumyadeep Pal, Ren Wang, Yuguang Yao, Sijia Liu

Recent studies on backdoor attacks in model training have shown that polluting a small portion of training data is sufficient to produce incorrect manipulated predictions on poisoned test-time data while maintaining high…

backdoor defenseRepresentation Learning