DIVA: Exploiting Cross-Step Conditional Propagation for Visual Jailbreaks in Discrete Diffusion Vision-Language Models

RESUMO

Large vision-language models (VLMs) are increasingly deployed in safety-critical settings, yet existing visual jailbreak research has focused almost exclusively on autoregressive architectures, leaving an important emerging family unstudied: multimodal discrete diffusion vision-language models (dVLMs). We identify a vulnerability specific to diffusion generation: because the visual embedding conditions every reverse denoising step rather than acting as a one-time prefix, adversarial visual semantics are repeatedly propagated and amplified across the generation trajectory, a phenomenon we term cross-step conditional propagation. We provide empirical evidence through stage-sensitivity analysis, prompt-level switch rates, and pairwise denoising-bin disagreement metrics, confirmed by bootstrap resampling. We propose DIVA (Discrete-diffusion Vision-language model Attack), a white-box visual jailbreak framework using cross-modal intent obfuscation and diffusion-aware multi-timestep adversarial optimization. Across three dVLMs, DIVA reaches 58.8%, 67.7%, and 69.1% HADES ASR under the Beaver reward-model metric, outperforming visual jailbreak baselines designed for autoregressive models. Code: this https URL