paper-with-me

홈 › Papers

PLA: Prompt Learning Attack against Text-to-Image Generative Models

2025-07-14 · Xinqi Lyu, Yihao Liu, Yanjie Li, Bin Xiao arxiv

Text-to-Image (T2I) models have gained widespread adoption across various applications. Despite the success, the potential misuse of T2I models poses significant risks of generating Not-Safe-For-Work (NSFW) content. To investigate the vulnerability of T2I models, this paper delves into adversarial attacks to bypass the safety mechanisms under black-box settings. Most previous methods rely on word substitution to search adversarial prompts. Due to limited search space, this leads to suboptimal performance compared to gradient-based training. However, black-box settings present unique challenges to training gradient-driven attack methods, since there is no access to the internal architecture and parameters of T2I models. To facilitate the learning of adversarial prompts in black-box settings, we propose a novel prompt learning attack framework (PLA), where insightful gradient-based training tailored to black-box T2I models is designed by utilizing multimodal similarities. Experiments show that our new method can effectively attack the safety mechanisms of black-box T2I models including prompt filters and post-hoc safety checkers with a high success rate compared to state-of-the-art methods. Warning: This paper may contain offensive model-generated content.

📄 PDF Abstract BibTeX arXiv:2508.03696

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models

2023-10-20 · Shawn Shan, Wenxin Ding, Josephine Passananti, Stanley Wu 외

Data poisoning attacks manipulate training data to introduce unexpected behaviors into machine learning models at training time. For text-to-image generative models with massive training datasets, current understanding o…

Data Poisoning

Image Hijacks: Adversarial Images can Control Generative Models at Runtime

2023-09-01 · Luke Bailey, Euan Ong, Stuart Russell, Scott Emmons

Are foundation models secure against malicious actors? In this work, we focus on the image input to a vision-language model (VLM). We discover image hijacks, adversarial images that control the behaviour of VLMs at infer…

Language ModelingLanguage Modelling

Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters

2026-04-02 · Ahmed B Mustafa, Zihan Ye, Yang Lu, Michael P Pound 외 arxiv

Text-to-image generative models are widely deployed in creative tools and online platforms. To mitigate misuse, these systems rely on safety filters and moderation pipelines that aim to block harmful or policy violating …

Understanding Implosion in Text-to-Image Generative Models

2024-09-18 · Wenxin Ding, Cathy Y. Li, Shawn Shan, Ben Y. Zhao 외

Recent works show that text-to-image generative models are surprisingly vulnerable to a variety of poisoning attacks. Empirical results find that these models can be corrupted by altering associations between individual …

Membership Inference Attacks for Face Images Against Fine-Tuned Latent Diffusion Models

2025-02-17 · Lauritz Christian Holme, Anton Mosquera Storgaard, Siavash Arjomand Bigdeli

The rise of generative image models leads to privacy concerns when it comes to the huge datasets used to train such models. This paper investigates the possibility of inferring if a set of face images was used for fine-t…

Inference AttackMembership Inference Attack