jonasrauber / linear-region-attack
A powerful white-box adversarial attack that exploits knowledge about the geometry of neural networks to find minimal adversarial perturbations without doing gradient descent
☆11Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for linear-region-attack
- Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]☆31Updated 4 years ago
- Logit Pairing Methods Can Fool Gradient-Based Attacks [NeurIPS 2018 Workshop on Security in Machine Learning]☆18Updated 5 years ago
- Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation [NeurIPS 2017]☆18Updated 6 years ago
- Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019☆46Updated last year
- Code for the Paper 'On the Connection Between Adversarial Robustness and Saliency Map Interpretability' by C. Etmann, S. Lunz, P. Maass, …☆16Updated 5 years ago
- Geometric Certifications of Neural Nets☆41Updated 2 years ago
- Implementation of Methods Proposed in Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks (NeurIPS 2019)☆33Updated 4 years ago
- Randomized Smoothing of All Shapes and Sizes (ICML 2020).☆51Updated 4 years ago
- Analysis of Adversarial Logit Pairing☆60Updated 6 years ago
- Code for Stability Training with Noise (STN)☆21Updated 3 years ago
- ☆31Updated 4 years ago
- [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.☆25Updated 3 months ago
- Investigating the robustness of state-of-the-art CNN architectures to simple spatial transformations.☆49Updated 5 years ago
- Benchmark for LP-relaxed robustness verification of ReLU-networks☆40Updated 5 years ago
- Public code for a paper "Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks."☆34Updated 5 years ago
- Code release for the ICML 2019 paper "Are generative classifiers more robust to adversarial attacks?"☆23Updated 5 years ago
- Code for "Testing Robustness Against Unforeseen Adversaries"☆80Updated 3 months ago
- Source code for the paper "Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness"☆26Updated 4 years ago
- ☆86Updated 3 months ago
- Code for "Robustness May Be at Odds with Accuracy"☆93Updated last year
- Codebase for "Exploring the Landscape of Spatial Robustness" (ICML'19, https://arxiv.org/abs/1712.02779).☆26Updated 5 years ago
- Code and data for the ICLR 2021 paper "Perceptual Adversarial Robustness: Defense Against Unseen Threat Models".☆54Updated 2 years ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆17Updated 5 years ago
- Implementation of Confidence-Calibrated Adversarial Training (CCAT).☆45Updated 4 years ago
- Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs☆96Updated 3 years ago
- Code implementing the experiments described in the NeurIPS 2018 paper "With Friends Like These, Who Needs Adversaries?".☆13Updated 4 years ago
- CVPR'19 experiments with (on-manifold) adversarial examples.☆44Updated 4 years ago
- Code for the paper "Understanding Generalization through Visualizations"☆60Updated 3 years ago
- Learning perturbation sets for robust machine learning☆64Updated 3 years ago
- A Closer Look at Accuracy vs. Robustness☆88Updated 3 years ago