Pith. sign in

REVIEW 3 cited by

SneakyPrompt: Jailbreaking Text-to-image Generative Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.12082 v3 pith:HIH4UA3U submitted 2023-05-20 cs.LG

classification cs.LG
keywords safetysneakypromptimagesnsfwgenerativetext-to-imagefiltersmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Text-to-image generative models such as Stable Diffusion and DALL$\cdot$E raise many ethical concerns due to the generation of harmful images such as Not-Safe-for-Work (NSFW) ones. To address these ethical concerns, safety filters are often adopted to prevent the generation of NSFW images. In this work, we propose SneakyPrompt, the first automated attack framework, to jailbreak text-to-image generative models such that they generate NSFW images even if safety filters are adopted. Given a prompt that is blocked by a safety filter, SneakyPrompt repeatedly queries the text-to-image generative model and strategically perturbs tokens in the prompt based on the query results to bypass the safety filter. Specifically, SneakyPrompt utilizes reinforcement learning to guide the perturbation of tokens. Our evaluation shows that SneakyPrompt successfully jailbreaks DALL$\cdot$E 2 with closed-box safety filters to generate NSFW images. Moreover, we also deploy several state-of-the-art, open-source safety filters on a Stable Diffusion model. Our evaluation shows that SneakyPrompt not only successfully generates NSFW images, but also outperforms existing text adversarial attacks when extended to jailbreak text-to-image generative models, in terms of both the number of queries and qualities of the generated NSFW images. SneakyPrompt is open-source and available at this repository: \url{https://github.com/Yuchen413/text2image_safety}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing

    cs.CV 2025-06 reject novelty 6.0 of 10

    SAGE erases concepts from diffusion models by optimizing attack prompts against the model's own text encoder and then fine-tuning that encoder with a global-local retention loss.

  2. Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation

    cs.CL 2025-08 reject novelty 5.0 of 10

    Sparse autoencoder activation perturbation (SFPF) applied on top of existing jailbreak prompts raises attack success rate on Qwen3-32B, but with no defense evaluation and weak reproducibility.

  3. Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message

    cs.AI 2025-07 reject novelty 5.0 of 10

    Trojan Horse Prompting injects malicious instructions into a fabricated assistant message in the API chat history, aiming to bypass Gemini's safety filters, but no quantitative evidence is provided.

Pith tools