{"data":{"id":"fd4a7c6d-03c2-47d9-8659-f2a2a3a7ec79","title":"No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation","summary":"IDGuardian is a model-agnostic identity protection framework that defends against both training-based and training-free personalized image generation with diffusion models. It splits personalization into identity extraction and identity injection, then adds adversarial perturbations to disrupt both stages. The authors report that it protects identity across various pipelines and architectures and stays robust to post-processing, adaptive attacks, and cross-dataset generalization.","solution":"The source describes a defensive framework (IDGuardian) that the authors propose, but it does not state a patch, fixed version, configuration change or workaround for users to apply. Code is available at https://github.com/OpenAscent-L/IDGuardian.git.","labels":["security","privacy"],"sourceUrl":"https://arxiv.org/abs/2610.19717v1","publishedAt":"2026-10-14T07:43:13.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["diffusion models"],"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":"2026-10-14T07:43:13.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}