Research map / Adversarial robustness and security / Attacks on text and graphs
TAFIM: Targeted Adversarial Attacks against Facial Image Manipulations
Shivangi Aneja, Lev Markhasin, Matthias Nießner
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace per-image optimization with a conditional perturbation network | I-PGD · Self-reconstruction | run time per image: 17523.01 ms -> 10.66 ms | Improved |
| condition perturbation model on global perturbation in addition to the image (ablation) | Ours Model (I) · Self-reconstruction (white target) | RMSE/PSNR/LPIPS/VGG vs perturbation level | Improved |
| train with differentiable JPEG compression (ablation) | TAFIM · Self-reconstruction under JPEG C-80 | protection quality | Improved |
| train with random compression quality instead of fixed C-80 (ablation) | TAFIM · Self-reconstruction under JPEG C-30 | protection quality | Improved |
| add attention-based fusion of model-specific perturbations (ablation) | Combined model · Multiple manipulations (pSp, SimSwap, StyleClip) | protection quality | Improved |
| use L2 norm instead of L1 or L-inf in the loss (ablation) | TAFIM · Self-reconstruction (white target) | PSNR vs perturbation | Improved |
| apply two successive JPEG compressions (C-30 then C-80) | TAFIM · Self-reconstruction | protection quality | No clear effect |
Closest papers by meaning
- Adversarial Robust Safeguard for Evading Deep Facial Manipulation (AAAI 2024 · similarity 0.88)
- Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial Obfuscation (ICML 2024 · similarity 0.85)
- DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection (CVPR 2024 · similarity 0.84)
- AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption (ICLR 2025 · similarity 0.84)
- Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models (NeurIPS 2024 · similarity 0.84)
- Harnessing Global-Local Collaborative Adversarial Perturbation for Anti-Customization (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
