PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors
Synthetic image detectors (SIDs) are a key defense against the risks posed by the growing realism of images from text-to-image (T2I) models. Red teaming improves SID's effectiveness by identifying and exploiting their failure modes via misclassified synthetic images. However, existing red-teaming solutions (i) require white-box access to SIDs, which is infeasible for proprietary state-of-the-art detectors, and (ii) generate image-specific attacks through expensive online optimization. To address these limitations, we propose PolyJuice, the first black-box, image-agnostic red-teaming method for SIDs, based on an observed distribution shift in the T2I latent space between samples correctly and incorrectly classified by the SID. PolyJuice generates attacks by (i) identifying the direction of this shift through a lightweight offline process that only requires black-box access to the SID, and (ii) exploiting this direction by universally steering all generated images towards the SID's failure modes. PolyJuice-steered T2I models are significantly more effective at deceiving SIDs (up to 84%) compared to their unsteered counterparts. We also show that the steering directions can be estimated efficiently at lower resolutions and transferred to higher resolutions using simple interpolation, reducing computational overhead. Finally, tuning SID models on PolyJuice-augmented datasets notably enhances the performance of the detectors (up to 30%).
Code (0)
등록된 구현이 없습니다.
Tasks
Red TeamingSimilar Papers 제목 키워드 기반
Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models
While counterfactual examples are useful for analysis and training of NLP models, current generation methods either rely on manual labor to create very few counterfactuals, or only instantiate limited types of perturbati…
counterfactualText GenerationQuery-Efficient Black-Box Red Teaming via Bayesian Optimization
The deployment of large-scale generative models is often restricted by their potential risk of causing harm to users in unpredictable ways. We focus on the problem of black-box red teaming, where a red team generates tes…
Bayesian OptimizationLanguage ModelingLanguage ModellingRed TeamingRed-teaming Activation Probes using Prompted LLMs
Activation probes are attractive monitors for AI systems due to low cost and latency, but their real-world robustness remains underexplored. We ask: What failure modes arise under realistic, black-box adversarial pressur…
Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations
Contrastive explanation methods go beyond transparency and address the contrastive aspect of explanations. Such explanations are emerging as an attractive option to provide actionable change to scenarios adversely impact…
Adversarial AttackAdversarial RobustnesscounterfactualSentiment AnalysisBlackIce: A Containerized Red Teaming Toolkit for AI Security Testing
AI models are being increasingly integrated into real-world systems, raising significant concerns about their safety and security. Consequently, AI red teaming has become essential for organizations to proactively identi…
Red Teaming