Paper deep dive
FlowJD: Your Imagination Can Help You Jailbreak in Visual Language Models
Xiaotian Zou, Yongkang Chen, Qianqian Han, Ke Li
Models: GPT-4o, GPT-4V
Intelligence
Status: succeeded | Model: google/gemini-3.1-flash-lite-preview | Prompt: intel-v1 | Confidence: 95%
Last extracted: 3/12/2026, 7:10:44 PM
Summary
The paper introduces FlowJD, a novel dataset designed to evaluate the vulnerability of Large Visual Language Models (VLMs) to logical flowchart-based jailbreak attacks. The study evaluates nine state-of-the-art VLMs, including GPT-4o and GPT-4V, finding high jailbreak success rates and highlighting critical security gaps in logical comprehension of image information.
Entities (4)
Relation Signals (3)
FlowJD → evaluates → Logical Flowchart Jailbreak
confidence 95% · FlowJD, specifically designed to evaluate logical flowchart jailbreak capabilities in VLMs.
GPT-4o → vulnerableto → Logical Flowchart Jailbreak
confidence 90% · We conduct a comprehensive evaluation on GPT-4o... revealing jailbreak rates of up to 92.8%.
GPT-4V → vulnerableto → Logical Flowchart Jailbreak
confidence 90% · We conduct a comprehensive evaluation on... GPT-4V... revealing jailbreak rates of up to 92.8%.
Cypher Suggestions (0)
No Cypher suggestions yet.
Abstract
Large Visual Language Models (VLMs), such as GPT-4V, have achieved impressive results in generating detailed and nuanced responses. Although researchers have proposed various benchmarks to evaluate VLM performance, they have often neglected the examination of inherent security capabilities, particularly by evaluating the logical comprehension of image information. To address this gap, this paper introduces a novel dataset, FlowJD, specifically designed to evaluate logical flowchart jailbreak capabilities in VLMs. We conduct a comprehensive evaluation on GPT-4o, GPT-4V, and seven other state-of-the-art VLMs, revealing jailbreak rates of up to 92.8%. Our findings reveal significant vulnerabilities in current VLMs concerning logical flowchart jailbreak, emphasizing the urgent need for robust and effective defenses in future VLM development.Warning: Some of the examples may be harmful!
Tags
Links
Full Text
822 characters extracted from source content.
Expand or collapse full text
FlowJD: Your Imagination Can Help You Jailbreak in Visual Language Models | IEEE Conference Publication | IEEE Xplore IEEE Account Change Username/Password Update Address Purchase Details Payment Options Order History View Purchased Documents Profile Information Communications Preferences Profession and Education Technical Interests Need Help? US & Canada: +1 800 678 4333 Worldwide: +1 732 981 0060 Contact & Support About IEEE Xplore Contact Us Help Accessibility Terms of Use Nondiscrimination Policy Sitemap Privacy & Opting Out of Cookies A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.© Copyright 2026 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.