Research map / Adversarial robustness and security / Backdoor and poisoning
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training
Zhenting Wang, Hailun Ding, Juan Zhai, Shiqing Ma
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 |
|---|---|---|---|
| apply NONE vs undefended training | BadNets single target, five datasets · Injected Trojans | average ASR (%): 93.34% -> 1.91% | Improved |
| apply NONE vs undefended training | natural Trojans · CIFAR-10 / TrojAI | ASR: 1.75 times lower ASR | Improved |
| NONE instead of ABL | label-specific BadNets · GTSRB ResNet18 | ASR (%): 93.93 -> 0.91 | Improved |
| NONE instead of DP-SGD | natural Trojan · CIFAR-10 NiN | ASR (%): 98.85 -> 34.21 | Improved |
| increase trigger size from 3*3 to 20*20 (ablation) | NONE · CIFAR-10 ResNet18 BadNets | ASR (%): 1.07 -> 99.82 | Hurt |
| increase poisoning rate from 0.5% to 20% (ablation) | NONE · CIFAR-10 ResNet18 BadNets | ASR (%): 2.52 -> 1.39 | No clear effect |
| use non-ReLU activations (ELU, Tanhshrink, Softplus) (ablation) | NONE · CIFAR-10 ResNet18 | ASR (%): 1.07 -> 1.46 / 5.11 / 2.07 | No clear effect |
| apply NONE to benign training | ImageNet-10 VGG16 · non-attack | benign accuracy (%): 88.84 -> 83.41 | Hurt |
| lower learning rate in NONE training (ablation) | NONE · CIFAR-10 ResNet18 | ASR | Mixed |
Closest papers by meaning
- Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness (NeurIPS 2024 · similarity 0.91)
- BAN: Detecting Backdoors Activated by Adversarial Neuron Noise (NeurIPS 2024 · similarity 0.90)
- BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection (ICLR 2024 · similarity 0.90)
- Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks (AAAI 2024 · similarity 0.89)
- BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model (NeurIPS 2025 · similarity 0.89)
- Adversarial-Inspired Backdoor Defense via Bridging Backdoor and Adversarial Attacks (AAAI 2025 · similarity 0.89)
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.
