Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step

TL;DR

This paper introduces the Chain-of-Jailbreak attack, a step-by-step method to bypass safety measures in image generation models, and proposes a defense strategy that effectively mitigates this attack, advancing AI safety research.

Contribution

The paper presents a novel multi-step jailbreaking attack for image generation models and a prompt-based defense, significantly improving safety evaluation and mitigation techniques.

Findings

CoJ attack bypasses safeguards in over 60% of cases

Proposed defense reduces successful attacks to over 95%

Constructed CoJ-Bench dataset for safety scenario evaluation

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 release our dataset and code to facilitate the AI safety research.