Location Matters: Sparse Latent-Variance Attacks for Face Privacy against Diffusion Personalization

Summary

The paper introduces SEAL, a sparse adversarial protection framework that modifies only 5% of spatial locations in a facial image to stop diffusion personalization from learning an individual's identity. It jointly optimizes perturbation locations and values through a differentiable top-k masking scheme, targeting the frozen VAE encoder's latent distribution. On CelebA-HQ and VGGFace2, it reports over 41 dB PSNR, 0.97 SSIM and at most 0.07 LPIPS, with identity similarity reduced to at most 0.15 after personalization.

Related items

• HighCVE-2026-63651: LiveDocs is a primary-source-first documentation for AI agents. Prior to version 0.7.0, fetch_docs and introspect…Similar attack · NVD/CVE Database
• HighCVE-2026-125271 - AWS API MCP Server Security Policy Bypass via Incorrect Operation Name NormalizationSimilar attack · AWS Security Bulletins
• MediumCVE-2026-83953 GitHub Copilot for Jetbrains Information Disclosure VulnerabilitySimilar attack · MSRC Security Update Guide
• HighGHSA-ghwv-vrp2-2975: Cocos AI Intra-handshake attested TLS implementation is vulnerable to TOCTOU AttacksSimilar attack · GitHub Advisory Database
• MediumGHSA-5m6c-38r8-5w76: Dagu MCP DAG specification read bypasses path containment and workspace isolationSimilar attack · GitHub Advisory Database