Research map / Adversarial robustness and security / Backdoor and poisoning
Enhancing All-to-X Backdoor Attacks with Optimized Target Class Mapping
Lei Wang, Yulong Tian, Hao Han, Fengyuan Xu
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 a single-trigger All-to-X attack (multiple target classes) instead of All-to-One | BadNets on CIFAR10 ResNet18 · CIFAR10 vs six defenses | ASR under defense: ABL: 2.0 -> 79.0 (X=1 vs X=10) | Improved |
| increase number of target classes X in A2X attack | A2X backdoor, existing mapping · CIFAR10 low poisoning rate 0.2% | ASR (%): 87.8 (A2O) -> 50.7 (X=5) -> 43.8 (X=10) | Hurt |
| replace random or cyclic target mapping with similarity-based grouping plus distance-aware target assignment | A2X backdoor attack · CIFAR10, CIFAR100, Tiny-ImageNet | ASR (%): avg +6.7%, +16.4%, +14.1% on CIFAR10, CIFAR100, Tiny-ImageNet | Improved |
| optimized mapping gains larger with more classes | A2X backdoor attack · CIFAR100 X=10 vs CIFAR10 | ASR (%): avg +25.8% (CIFAR100 X=10); +5.8% (CIFAR10 X=10) | Improved |
| optimized mapping at 0.5% poisoning on Tiny-ImageNet | A2X backdoor attack · Tiny-ImageNet | ASR (%) | No clear effect |
| optimized mapping under six backdoor defenses | A2X backdoor attack · CIFAR10 ResNet18 defenses | ASR (%): better in 58 of 72 settings; gains 0.3% to 43.1% | Mixed |
| use a surrogate model with different architecture or optimizer than victim | optimized A2X attack · CIFAR10 X=5 | ASR (%): within 3.28% of same-config results | No clear effect |
| keep only one of grouping or target assignment components (ablation) | optimized A2X attack · CIFAR10, CIFAR100, Tiny-ImageNet | ASR (%) | Improved |
Closest papers by meaning
- Protecting against simultaneous data poisoning attacks (ICLR 2025 · similarity 0.88)
- Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors (NeurIPS 2026 · similarity 0.85)
- LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect (NeurIPS 2024 · similarity 0.85)
- Robustness Inspired Graph Backdoor Defense (ICLR 2025 · similarity 0.85)
- Closing the Gap: Achieving Better Accuracy-Robustness Tradeoffs against Query-Based Attacks (AAAI 2024 · similarity 0.84)
- Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks (AAAI 2024 · 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.
