{"data":{"id":"798da765-5089-43f5-bce2-bf95221f5348","title":"Mirage: Targeted Jailbreaks Against Post-Generation Safety Checkers in Multimodal Diffusion Models","summary":"Researchers present Mirage, a multimodal jailbreak attack that bypasses post-generation safety checkers in diffusion pipelines. Mirage hides an adversarial target, either a reference NSFW image or a malicious text description, inside an imperceptible perturbation on a benign input image, exploiting the shared representation space of multimodal encoders. The authors report targeted jailbreak success against Stable Diffusion 1.5, Stable Diffusion XL, and Kandinsky 2.2 using limited black-box queries.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.30348v1","publishedAt":"2026-10-21T19:08:24.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak","model_evasion"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Stability AI"],"affectedVendorsRaw":["Stable Diffusion 1.5","Stable Diffusion XL","Kandinsky 2.2"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-21T19:08:24.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety","integrity"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}