BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models
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 PromptingAEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis
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
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
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
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…