Research map / Adversarial robustness and security / Attacks on text and graphs
Bit-Flip Attack: Crushing Neural Network With Progressive Bit Search
Adnan Siraj Rakin, Zhezhi He, Deliang Fan
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 progressive bit search instead of random bit flips (ablation) | bit-flip attack on 8-bit ResNet-18 · ImageNet | top-1 accuracy: 100 random flips cost under 1% vs 13 PBS flips reach 0.1% | Improved |
| attack only the first conv layer instead of only the last linear layer (ablation) | BFA on VGG16 · CIFAR-10 | top-1 accuracy (%): 84.61 -> 10.06 | Improved |
| use attack sample size 128 instead of 16 (ablation) | BFA with PBS · CIFAR-10 / ImageNet | bit-flips needed | Improved |
| use a very large or very small attack sample size (ablation) | BFA with PBS · ImageNet ResNet-18 | attack strength | Mixed |
| randomly flip one bit in a full-precision floating-point weight (ablation) | ResNet-18 · ImageNet | accuracy | Hurt |
| lower quantization bit-width from 8 to 4 | BFA with PBS · CIFAR-10 | accuracy after attack | No clear effect |
| increase network depth/params from ResNet-18 to ResNet-34 | BFA with PBS · ImageNet | bit-flips to crush: 13 -> 11 | Improved |
Closest papers by meaning
- Versatile Weight Attack via Flipping Limited Bits (TPAMI 2023 · similarity 0.92)
- Crossfire: An Elastic Defense Framework for Graph Neural Networks Under Bit Flip Attacks (AAAI 2025 · similarity 0.85)
- Deep-TROJ: An Inference Stage Trojan Insertion Algorithm through Efficient Weight Replacement Attack (CVPR 2024 · similarity 0.84)
- Your Scale Factors are My Weapon: Targeted Bit-Flip Attacks on Vision Transformers via Scale Factor Manipulation (CVPR 2025 · similarity 0.84)
- S$^2$NN: Sub-bit Spiking Neural Networks (NeurIPS 2025 · similarity 0.82)
- SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models (NeurIPS 2025 · similarity 0.82)
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.
