paper-with-me

Papers

BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation

2026-03-06 · Feiran Li, Qianqian Xu, Shilong Bao, Zhiyong Yang, Xilin Zhao, Xiaochun Cao, Qingming Huang arxiv

This paper investigates the challenging task of detecting backdoored text-to-image models under black-box settings and introduces a novel detection framework BlackMirror. Existing approaches typically rely on analyzing image-level similarity, under the assumption that backdoor-triggered generations exhibit strong consistency across samples. However, they struggle to generalize to recently emerging backdoor attacks, where backdoored generations can appear visually diverse. BlackMirror is motivated by an observation: across backdoor attacks, {only partial semantic patterns within the generated image are steadily manipulated, while the rest of the content remains diverse or benign. Accordingly, BlackMirror consists of two components: MirrorMatch, which aligns visual patterns with the corresponding instructions to detect semantic deviations; and MirrorVerify, which evaluates the stability of these deviations across varied prompts to distinguish true backdoor behavior from benign responses. BlackMirror is a general, training-free framework that can be deployed as a plug-and-play module in Model-as-a-Service (MaaS) applications. Comprehensive experiments demonstrate that BlackMirror achieves accurate detection across a wide range of attacks. Code is available at https://github.com/Ferry-Li/BlackMirror.

📄 PDF Abstract BibTeX arXiv:2603.05921

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models

2024-11-14 · Zi-Xuan Huang, Jia-Wei Chen, Zhi-Peng Zhang, Chia-Mu Yu

Visual prompting (VP) is a new technique that adapts well-trained frozen models for source domain tasks to target domain tasks. This study examines VP's benefits for black-box model-level backdoor detection. The visual p…

Visual Prompting

AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis

2021-10-28 · ICLR 2022 4 · Junfeng Guo, Ang Li, Cong Liu

Deep neural networks (DNNs) are proved to be vulnerable against backdoor attacks. A backdoor is often embedded in the target DNNs through injecting a backdoor trigger into training examples, which can cause the target DN…

Black-box Detection of Backdoor Attacks with Limited Information and Data

2021-03-24 · ICCV 2021 10 · Yinpeng Dong, Xiao Yang, Zhijie Deng, Tianyu Pang 외

Although deep neural networks (DNNs) have made rapid progress in recent years, they are vulnerable in adversarial environments. A malicious backdoor could be embedded in a model by poisoning the training dataset, whose i…

UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models

2024-04-01 · Zihan Guan, Mengxuan Hu, Sheng Li, Anil Vullikanti

Diffusion models are vulnerable to backdoor attacks, where malicious attackers inject backdoors by poisoning certain training samples during the training stage. This poses a significant threat to real-world applications …

Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models

2025-08-30 · Zuquan Peng, Jianming Fu, Lixin Zou, Li Zheng 외 arxiv

The use of unvetted third-party and internet data renders pre-trained models susceptible to backdoor attacks. Detecting backdoor samples is critical to prevent backdoor activation during inference or injection during tra…