Research map / Adversarial robustness and security / Backdoor and poisoning
WaNet - Imperceptible Warping-based Backdoor Attack
Tuan Anh Nguyen, Anh Tuan Tran
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 |
|---|---|---|---|
| Use elastic image warping as the trigger instead of added patch or noise perturbations | WaNet · GTSRB human inspection | success fooling rate: up to 7.7% -> 28% | Improved |
| Add the noise training mode around the fixed warping field (ablation) | WaNet · CIFAR-10, Neural Cleanse | defense detection | Improved |
| Remove the noise training mode (ablation) | WaNet · CIFAR-10, Neural Cleanse | defense detection | Hurt |
| Use small warping strength or grid size (ablation) | WaNet · CIFAR-10 | backdoor accuracy | Hurt |
| Increase warping strength or grid size from small values (ablation) | WaNet · CIFAR-10 | backdoor accuracy | Improved |
| Vary the randomly generated warping field (ablation) | WaNet · CIFAR-10 | clean accuracy: 94.42 ± 0.08 | No clear effect |
| Vary the randomly generated warping field (ablation) | WaNet · CIFAR-10 | backdoor accuracy: 99.40 ± 0.21 | No clear effect |
| Vary the randomly generated warping field (ablation) | WaNet · CIFAR-10 | noise accuracy: 93.16 ± 0.43 | No clear effect |
| Switch from all-to-one to all-to-all target labels (ablation) | WaNet · MNIST, CIFAR-10, GTSRB, and CelebA | attack accuracy | Hurt |
| Use the fixed warp for physical screen recapture attacks | WaNet · Physical screen recapture | attack success rate: 96% | Improved |
Later papers that compared with this method
14 later accepted papers report WaNet as a baseline in their results tables; 12 of them report a better number on most of the results they share with it.
- Backdoor Attacks under Lossy Compression: From Failure to Reactivation and Adaptation (NeurIPS 2026 · better on 4 of 4 shared results)
- Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning (AAAI 2026 · better on 4 of 4 shared results)
- Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model Reuse (NeurIPS 2026 · better on 2 of 2 shared results)
- Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures (CVPR 2026 · better on 2 of 2 shared results)
- Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization (AAAI 2026 · better on 1 of 1 shared result)
- Versatile Backdoor Attack With Visible, Semantic, Sample-Specific and Compatible Triggers (TPAMI 2025 · better on 2 of 3 shared results)
- Attention-Imperceptible Backdoor Attacks on Vision Transformers (AAAI 2025 · better on 2 of 2 shared results)
- Conditional Backdoor Attack via JPEG Compression (AAAI 2024 · better on 0 of 1 shared result)
6 more not listed.
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- BAN: Detecting Backdoors Activated by Adversarial Neuron Noise (NeurIPS 2024 · similarity 0.88)
- Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks (AAAI 2024 · similarity 0.87)
- BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model (NeurIPS 2025 · similarity 0.87)
- LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning (CVPR 2024 · similarity 0.87)
- Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective (ICLR 2024 · similarity 0.87)
- From Toxic to Trustworthy: Using Self-Distillation and Semi-supervised Methods to Refine Neural Networks (AAAI 2024 · 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.
