Research map / Adversarial robustness and security / Certified and empirical robustness
Certified but Fooled! Breaking Certified Defenses with Ghost Certificates
Quoc Viet Vo, Tashreque Mohammed Haq, Paul Montague, Tamas Abraham, Ehsan Abbasnejad, Damith C. Ranasinghe
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 |
|---|---|---|---|
| restrict perturbation to SAM+GradCAM salient-region mask (GhostCert) instead of global perturbation (Shadow Attack) | Randomized Smoothing ensemble · ImageNet untargeted | attack success rate (%): 40% -> ~100% (sigma=0.25) | Improved |
| GhostCert vs Shadow Attack in targeted attack on ensemble | Randomized Smoothing ensemble · ImageNet targeted | attack success rate (%): 20% -> over 80% (sigma=0.25) | Improved |
| GhostCert vs Shadow Attack on DensePure | DensePure · ImageNet untargeted sigma=0.25 | spoofed radius | No clear effect |
| GhostCert vs Shadow Attack on DensePure | DensePure · ImageNet untargeted sigma=0.25 | attack success rate (%): 30-65% -> 30-100% | Improved |
| increase distortion budget from 2 to 6 in user study (ablation) | GhostCert · User study naturalness | % choosing GhostCert: 74 -> 58 | Hurt |
| switch ensemble defense to larger noise (sigma 0.5, 1.0) (ablation) | GhostCert targeted attack on ensemble · ImageNet targeted | attack success rate | Hurt |
Closest papers by meaning
- BREAKING CERTIFIED DEFENSES: SEMANTIC ADVERSARIAL EXAMPLES WITH SPOOFED ROBUSTNESS CERTIFICATES (ICLR 2020 · similarity 0.91)
- Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples (ICML 2024 · similarity 0.91)
- Position: Certified Robustness Does Not (Yet) Imply Model Security (ICML 2025 · similarity 0.91)
- On the Scalability of Certified Adversarial Robustness with Generated Data (NeurIPS 2024 · similarity 0.89)
- Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing (ICML 2025 · similarity 0.88)
- Learning Better Certified Models from Empirically-Robust Teachers (NeurIPS 2026 · similarity 0.87)
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.
