Research map / Adversarial robustness and security / Certified and empirical robustness
Combinatorial Attacks on Binarized Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 IProp instead of iterated FGSM | BNN adversarial attacks · MNIST and Fashion-MNIST | attack success rate | Helped |
| Use IProp instead of iterated FGSM | BNN adversarial attacks · MNIST | normalized objective value | Helped |
| Use IProp instead of the full-network MILP | BNN adversarial attacks · MNIST and Fashion-MNIST | attack success rate | Mixed |
| Use an adaptive step size instead of a constant step size (ablation) | IProp · MNIST, varying network sizes and perturbation budgets | attack success rate | Mixed |
| Warm start IProp with a perturbation found by 5 seconds of FGSM instead of zero perturbation (ablation) | IProp · MNIST | attack success rate | Helped |
Closest papers by meaning
- Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits (ICLR 2021 · similarity 0.88)
- Verifying Properties of Binary Neural Networks Using Sparse Polynomial Optimization (ICLR 2025 · similarity 0.86)
- Taming Binarized Neural Networks and Mixed-Integer Programs (AAAI 2024 · similarity 0.85)
- Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming (NeurIPS 2024 · similarity 0.84)
- Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks (NeurIPS 2025 · similarity 0.82)
- Crossfire: An Elastic Defense Framework for Graph Neural Networks Under Bit Flip Attacks (AAAI 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.