Research map / Adversarial robustness and security / Attacks on text and graphs
Creating Blank Canvas Against AI-enabled Image Forgery
Qi Song, Ziyuan Luo, Renjie Wan
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 |
|---|---|---|---|
| protect images with blank-canvas adversarial perturbation before tampering (ablation) | SAM tamper localization · Ablation (tamper localization) | F1: 0.352 -> 0.964 | Improved |
| add frequency-aware optimization (L_stealth plus adaptive spectral step) to MSE attack (ablation) | blank canvas perturbation · Ablation (tamper localization) | F1: 0.934 -> 0.964 | Improved |
| add frequency-aware optimization (ablation) | blank canvas perturbation · Ablation (tamper localization) | IoU: 0.928 -> 0.955 | Improved |
| add random degradation to protected images before tampering (ablation) | full method · Ablation (tamper localization) | F1: 0.964 -> 0.945 | Hurt |
| use proactive blank-canvas protection instead of passive detectors | AIGC-edited images (AGE-Set) · AGE-Set SD Inpaint | F1: 0.694 -> 0.972 | Improved |
| blank-canvas SAM vs EditGuard on classical benchmarks | tamper localization · CASIA1+ | F1: 0.67 -> 0.67 | No clear effect |
| blank-canvas SAM vs EditGuard on AIGC edits | tamper localization · AGE-Set RePaint | F1: 0.967 -> 0.961 | Hurt |
| blank-canvas SAM vs EditGuard on Korus | tamper localization · Korus | F1: 0.28 -> 0.31 | Improved |
Closest papers by meaning
- Learning Discriminative Noise Guidance for Image Forgery Detection and Localization (AAAI 2024 · similarity 0.86)
- FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models (ICLR 2025 · similarity 0.86)
- DarkSAM: Fooling Segment Anything Model to Segment Nothing (NeurIPS 2024 · similarity 0.85)
- A Lottery Ticket Hypothesis Approach with Sparse Fine-tuning and MAE for Image Forgery Detection and Localization (AAAI 2025 · similarity 0.85)
- Revisiting Tampered Scene Text Detection in the Era of Generative AI (AAAI 2025 · similarity 0.84)
- SAFIRE: Segment Any Forged Image Region (AAAI 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.
