- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper proposes GenShield, a generalizable visual prompt defense against vision-language model (VLM) jailbreak attacks. To improve cross-attack generalization, it employs beam search to construct strong composite attacks during adversarial training. To enhance cross-scene generalization, it introduces dual-direction mutual information regularization that strengthens the dependence between visual prompts and prompt-induced decision changes while reducing their dependence on image content. The framework optimizes a universal visual prompt within approximately 2% of the image without modifying VLM parameters. Experiments on multiple VLMs and benchmarks demonstrate promising defense effectiveness and generalization while largely preserving benign utility and visual fidelity.
Critical strengths
- This paper addresses generalization from both attack-space coverage and scene dependency perspectives, combining compositional attack search with mutual information regularization in a well-motivated framework.
- The dual-direction mutual information regularization based on prompt-induced decision changes is an interesting design, achieving promising cross-attack generalization while modifying only about 2% of the image and largely preserving benign utility.
Critical weaknesses
- The overall methodological novelty is limited, as the framework largely builds upon SafeLogo [1], while adversarial prompt optimization [2] and search-based attack generation [3] have been extensively studied.
- The necessity of the proposed mutual information regularization remains unclear, as comparisons with simpler alternatives, such as decision-change variance minimization or cross-scene consistency regularization, are missing.
- This paper claims that compositional beam search improves attack-space coverage but provides no direct evidence of increased attack diversity or coverage, nor comparisons with simpler composition strategies under matched query budgets.
- The provided training script disables online compositional attack search, and the required external search implementation is not included in the released code. Additionally, the code introduces training components not clearly described in the paper, raising concerns about implementation consistency and reproducibility.
[1] Duan, Z., et al. SafeLogo: Turning Your Logos into Jailbreak Shields via Micro-Regional Adversarial Training.
[2] Mo, Y., et al. Fight Back Against Jailbreaking via Prompt Adversarial Tuning.
[3] Mehrotra, A., et al. Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.
Questions for authors
- Under matched attack-query and training budgets, how does compositional beam search compare with SafeLogo's adaptive attack selection [1], random strategy composition, and search-based alternatives inspired by TAP [2]?
- Can the authors provide quantitative evidence that compositional search improves attack-space coverage rather than simply generating stronger or more numerous attacks?
- Why are InfoNCE and conditional vCLUB preferable to simpler decision-change consistency or variance regularization, and can the authors provide corresponding comparisons?
- Can the authors clarify whether the experiments use the additional safety text prefix and benign refusal penalty found in the released code, and provide the complete compositional attack search implementation?
[1] Duan, Z., et al. SafeLogo: Turning Your Logos into Jailbreak Shields via Micro-Regional Adversarial Training.
[2] Mehrotra, A., et al. Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.
10 comments
W1-Methodological novelty. The overall methodological novelty is limited, as the framework largely builds upon SafeLogo [1], while adversarial prompt optimization [2] and search-based attack generation [3] have been extensively studied.
Response. Thank you for encouraging us to clarify our methodological contribution. GenShield jointly addresses limited training attack coverage and dependence on visual scenes, two factors that the cited methods do not explicitly target together, to improve generalization across attacks and visual scenes. Our compositional search and MI regularization can also be incorporated into other visual-prompt defenses. We clarify the distinctions from the three cited works below.
-
Distinction from SafeLogo [1]. We adopt SafeLogo’s adversarial training framework because its localized visual prompt offers a practical balance between defense effectiveness and benign utility. SafeLogo’s key insight is to balance defense effectiveness and benign utility, while GenShield builds on these advantages to explicitly address attack coverage and scene dependence, two factors affecting defense generalization. Our compositional search and MI regularization can also be incorporated into other trainable visual-prompt defenses, not just SafeLogo.
-
Distinction from Prompt Adversarial Tuning [2]. PAT optimizes a textual defense prefix using adversarial and benign objectives. These objectives do not explicitly model attack-strategy coverage or visual-scene dependence. GenShield introduces training mechanisms explicitly targeting these two generalization factors: compositional search broadens training attack coverage, while MI regularization encourages decision changes to depend more on the visual prompt and less on the visual scene. Together, they target generalization across both attacks and visual scenes.
-
Distinction from Tree of Attacks [3]. TAP iteratively generates and refines attack prompts using model feedback to find a successful jailbreak. GenShield explicitly searches over combinations of attack strategies, generating composed attacks for visual-prompt training. Table R2 shows that these composed attacks improves attack-space coverage. This provides evidence that explicit strategy composition broadens the attack coverage used to train the defense.
References
[1] Duan, Z., et al. SafeLogo: Turning Your Logos into Jailbreak Shields via Micro-Regional Adversarial Training. CVPR, 2026.
[2] Mo, Y., et al. Fight Back Against Jailbreaking via Prompt Adversarial Tuning. NeurIPS, 2024.
[3] Mehrotra, A., et al. Tree of Attacks: Jailbreaking Black-Box LLMs Automatically. NeurIPS, 2024.
W2-Necessity of MI regularization. The necessity of the proposed mutual information regularization remains unclear, as comparisons with simpler alternatives, such as decision-change variance minimization or cross-scene consistency regularization, are missing.
Q3-Comparison with simpler regularizers. Why are InfoNCE and conditional vCLUB preferable to simpler decision-change consistency or variance regularization, and can the authors provide corresponding comparisons?
Response. Thank you for suggesting these comparisons to clarify the role of MI regularization. Both simpler alternatives encourage similar decision changes across samples, but neither explicitly strengthens the dependence of these changes on the visual prompt. Our MI formulation combines two objectives: InfoNCE encourages stronger prompt dependence, while conditional vCLUB reduces visual scene dependence given the prompt. This “push–pull” design aims to reduce reliance on scene-specific cues, supporting generalization to new scenes without requiring identical adjustments across inputs. Together with the safety and benign objectives, this formulation achieves a better balance between defense effectiveness and benign utility than the simpler alternatives in Table R1.
-
Compared with decision-change variance minimization.
Decision-change variance minimization penalizes variation in decision changes across samples, encouraging similar adjustments regardless of intent. However, different inputs may need different adjustments to reach safe outcomes. Pulling these adjustments toward a common value may produce a compromise that works on training images but provides insufficient correction in more challenging unseen scenes. Our MI formulation instead encourages decision changes to depend more on the visual prompt and less on the visual scene, without requiring the same amount of adjustment for every input.
-
Compared with cross-scene consistency regularization.
Restricting consistency to scenes sharing the same harmful intent makes the constraint more targeted. However, these scenes may still require different amounts of correction. Encouraging similar changes can therefore lead to unnecessarily large adjustments for samples needing only minor correction. Since the same visual prompt is also applied to benign inputs, this tendency may interfere with legitimate responses. Our MI formulation instead regulates prompt and scene dependence without directly matching the adjustment magnitudes.
-
Experimental comparison.
To evaluate these design choices empirically, we compare both alternatives with our MI formulation, training without MI, and the undefended model. For cross-scene consistency regularization, we use the three images (SD, SD_TYPO, and TYPO) corresponding to each harmful intent in MM-SafetyBench and minimize the variance of their decision changes. Table R1 shows that our MI formulation better balances defense effectiveness and benign utility.
Table R1. Comparison with simpler decision-change regularizers. Cross-attack evaluation uses GPTFuzzer (ASR@5), and cross-scene evaluation uses PAIR on VLGuard. ASR is reported in % (↓); higher MM-Vet is better (↑).
Configuration Cross-attack ASR@5 Cross-scene ASR MM-Vet No defense 42.00 29.41 36.9 Without MI 33.00 15.16 34.7 Decision-change variance minimization 29.00 15.61 35.3 Cross-scene consistency regularization 29.00 13.57 34.2 InfoNCE + conditional vCLUB 29.00 12.67 36.6
Thank you for your helpful comments and suggestions. We have added the attack-construction strategy comparison to Section 6.4, the textual strategy coverage analysis to Appendix E.1, and comparisons with simpler regularizers to Appendix E.4. We have also clarified the safety text prefix, benign refusal penalty in the implementation details appendix. The corresponding additions are highlighted in blue for ease of reference.