{"data":{"id":"15478c97-c72b-484d-b74c-abd550551698","title":"Patronus: Safeguarding Text-to-Image Models Against Adversarial Fine-Tuning","summary":"Patronus is a defensive framework that hardens text-to-image models against gradient-based adversarial fine-tuning attacks that try to restore unsafe generation. It pairs a co-trained safety decoder, which corrupts output for latent representations tied to unsafe content, with a non-fine-tunable learning mechanism applied to the decoder and U-Net. Across I2P, SneakyPrompt and MMA-Diffusion, it reports attack success rates of 0.01 to 0.03 and true positive rates of 0.98 to 0.99, with FID 23.6, LPIPS 0.78 and a 0.01 false positive rate on benign prompts.","solution":"Patronus: co-trained safety decoder that corrupts output for unsafe latent representations, plus a non-fine-tunable learning mechanism for the decoder and U-Net.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11653447","publishedAt":"2026-08-12T13:16:39.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"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":"2026-08-12T13:16:39.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety","integrity"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.95,"researchCategory":"peer_reviewed","atlasIds":["AML.T0054"]}}