paper-with-me

홈 › Papers

A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models

2025-02-26 · Vu Tuan Truong, Long Bao Le

Diffusion models have emerged as state-of-the-art generative frameworks, excelling in producing high-quality multi-modal samples. However, recent studies have revealed their vulnerability to backdoor attacks, where backdoored models generate specific, undesirable outputs called backdoor target (e.g., harmful images) when a pre-defined trigger is embedded to their inputs. In this paper, we propose PureDiffusion, a dual-purpose framework that simultaneously serves two contrasting roles: backdoor defense and backdoor attack amplification. For defense, we introduce two novel loss functions to invert backdoor triggers embedded in diffusion models. The first leverages trigger-induced distribution shifts across multiple timesteps of the diffusion process, while the second exploits the denoising consistency effect when a backdoor is activated. Once an accurate trigger inversion is achieved, we develop a backdoor detection method that analyzes both the inverted trigger and the generated backdoor targets to identify backdoor attacks. In terms of attack amplification with the role of an attacker, we describe how our trigger inversion algorithm can be used to reinforce the original trigger embedded in the backdoored diffusion model. This significantly boosts attack performance while reducing the required backdoor training time. Experimental results demonstrate that PureDiffusion achieves near-perfect detection accuracy, outperforming existing defenses by a large margin, particularly against complex trigger patterns. Additionally, in an attack scenario, our attack amplification approach elevates the attack success rate (ASR) of existing backdoor attacks to nearly 100\% while reducing training time by up to 20x.

📄 PDF Abstract BibTeX arXiv:2502.19047

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor Attackbackdoor defenseDenoising

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

On the Trade-off between Adversarial and Backdoor Robustness

2020-12-01 · NeurIPS 2020 12 · Cheng-Hsin Weng, Yan-Ting Lee, Shan-Hung (Brandon) Wu

Deep neural networks are shown to be susceptible to both adversarial attacks and backdoor attacks. Although many defenses against an individual type of the above attacks have been proposed, the interactions between the v…

Adversarial Robustness

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

2023-11-20 · CVPR 2024 1 · Siyuan Liang, Mingli Zhu, Aishan Liu, Baoyuan Wu 외

Studying backdoor attacks is valuable for model copyright protection and enhancing defenses. While existing backdoor attacks have successfully infected multimodal contrastive learning models such as CLIP, they can be eas…

Backdoor AttackContrastive Learning

Magnitude-based Neuron Pruning for Backdoor Defens

2024-05-28 · Nan Li, Haoyu Jiang, Ping Yi

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks, posing concerning threats to their reliable deployment. Recent research reveals that backdoors can be erased from infected DNNs by pruning a spe…

backdoor defense

Backdoor attacks and defenses in feature-partitioned collaborative learning

2020-07-07 · Yang Liu, Zhihao Yi, Tianjian Chen

Since there are multiple parties in collaborative learning, malicious parties might manipulate the learning process for their own purposes through backdoor attacks. However, most of existing works only consider the feder…

Federated Learning

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE

2023-05-24 · Qin Liu, Fei Wang, Chaowei Xiao, Muhao Chen

Language models are often at risk of diverse backdoor attacks, especially data poisoning. Thus, it is important to investigate defense solutions for addressing them. Existing backdoor defense methods mainly focus on back…

backdoor defenseData PoisoningDenoisingSentence+1