Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step
Keywords: Jailbreak Attack, Text-to-Image Models, Safety
TL;DR: We introduce a novel Chain-of-Jailbreak (CoJ) attack method, which compromises image generation models through a step-by-step editing process.
Abstract: Text-based image generation models, such as Stable Diffusion and DALL-E 3, hold significant potential in content creation and publishing workflows, making them the focus in recent years.
Despite their remarkable capability to generate diverse and vivid images, considerable efforts are being made to prevent the generation of harmful content, such as abusive, violent, or pornographic material.
To assess the safety of existing models, we introduce a novel jailbreaking method called Chain-of-Jailbreak (CoJ) attack, which compromises image generation models through a step-by-step editing process.
Specifically, for malicious queries that cannot bypass the safeguards with a single prompt, we intentionally decompose the query into multiple sub-queries. The image generation models are then prompted to generate and iteratively edit images based on these sub-queries.
To evaluate the effectiveness of our CoJ attack method, we constructed a comprehensive dataset, CoJ-Bench, encompassing nine safety scenarios, three types of editing operations, and three editing elements.
Experiments on four widely-used image generation services provided by GPT-4V, GPT-4o, Gemini 1.5 and Gemini 1.5 Pro, demonstrate that our CoJ attack method can successfully bypass the safeguards of models for over 60\% cases, which significantly outperforms other jailbreaking methods (i.e., 14\%).
Further, to enhance these models' safety against our CoJ attack method, we also propose an effective prompting-based method, Think Twice Prompting, that can successfully defend over 95\% of CoJ attack.
We will release our dataset and code to facilitate the AI safety research.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 8521
Loading