paper-with-me

홈 › Papers

Backdoors in Conditional Diffusion: Threats to Responsible Synthetic Data Pipelines

2025-07-07 · Raz Lapid, Almog Dubin arxiv

Text-to-image diffusion models achieve high-fidelity image generation from natural language prompts. ControlNets extend these models by enabling conditioning on structural inputs (e.g., edge maps, depth, pose), providing fine-grained control over outputs. Yet their reliance on large, publicly scraped datasets and community fine-tuning makes them vulnerable to data poisoning. We introduce a model-poisoning attack that embeds a covert backdoor into a ControlNet, causing it to produce attacker-specified content when exposed to visual triggers, without textual prompts. Experiments show that poisoning only 1% of the fine-tuning corpus yields a 90-98% attack success rate, while 5% further strengthens the backdoor, all while preserving normal generation quality. To mitigate this risk, we propose clean fine-tuning (CFT): freezing the diffusion backbone and fine-tuning only the ControlNet on a sanitized dataset with a reduced learning rate. CFT lowers attack success rates on held-out data. These results expose a critical security weakness in open-source, ControlNet-guided diffusion pipelines and demonstrate that CFT offers a practical defense for responsible synthetic-data pipelines.

📄 PDF Abstract BibTeX arXiv:2507.04726

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Invisible Backdoor Attacks on Diffusion Models

2024-06-02 · Sen Li, Junchi Ma, Minhao Cheng

In recent years, diffusion models have achieved remarkable success in the realm of high-quality image generation, garnering increased attention. This surge in interest is paralleled by a growing concern over the security…

Backdoor AttackHuman DetectionImage Generationtext-guided-image-editing

Securing Federated Learning against Backdoor Threats with Foundation Model Integration

2024-10-23 · Xiaohuan Bi, Xi Li

Federated Learning (FL) enables decentralized model training while preserving privacy. Recently, the integration of Foundation Models (FMs) into FL has enhanced performance but introduced a novel backdoor attack mechanis…

Backdoor AttackFederated Learning

Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs

2026-03-08 · Yige Li, Wei Zhao, Zhe Li, Nay Myat Min 외 arxiv

Backdoor mechanisms have traditionally been studied as security threats that compromise the integrity of machine learning models. However, the same mechanism -- the conditional activation of specific behaviors through in…

UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning

2025-01-26 · Oubo Ma, Linkang Du, Yang Dai, Chunyi Zhou 외

Deep reinforcement learning (DRL) is widely applied to safety-critical decision-making scenarios. However, DRL is vulnerable to backdoor attacks, especially action-level backdoors, which pose significant threats through …

Backdoor AttackDeep Reinforcement Learning

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models

2025-11-24 · Juncheng Li, Yige Li, Hanxun Huang, Yunhao Chen 외 arxiv

Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studi…

Visual Question AnsweringImage Captioning