A powerful white-box adversarial attack that exploits knowledge about the geometry of neural networks to find minimal adversarial perturbations without doing gradient descent
☆12Aug 5, 2020Updated 5 years ago
Alternatives and similar repositories for linear-region-attack
Users that are interested in linear-region-attack are comparing it to the libraries listed below
Sorting:
- Provable Robustness of ReLU networks via Maximization of Linear Regions [AISTATS 2019]☆31Jul 15, 2020Updated 5 years ago
- Logit Pairing Methods Can Fool Gradient-Based Attacks [NeurIPS 2018 Workshop on Security in Machine Learning]☆19Dec 2, 2018Updated 7 years ago
- Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation [NeurIPS 2017]☆18Apr 8, 2018Updated 7 years ago
- ☆13Jun 23, 2022Updated 3 years ago
- FuseLIP: Multimodal Embeddings via Early Fusion of Discrete Tokens☆17Sep 8, 2025Updated 5 months ago
- Comparison of gradient estimation techniques for black-box adversarial examples☆11Oct 31, 2018Updated 7 years ago
- ☆11Jan 26, 2020Updated 6 years ago
- Source-to-Source Debuggable Derivatives in Pure Python☆15Jan 23, 2024Updated 2 years ago
- Code for "Robustness May Be at Odds with Accuracy"☆91Mar 24, 2023Updated 2 years ago
- Geometric Certifications of Neural Nets☆42Nov 22, 2022Updated 3 years ago
- [ECCV 2024] Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models☆21Jul 17, 2024Updated last year
- [CVPR 2024] This repository includes the official implementation our paper "Revisiting Adversarial Training at Scale"☆20Apr 21, 2024Updated last year
- Chain-of-Frames [CVPR 2026]☆38Jul 2, 2025Updated 8 months ago
- Interval attacks (adversarial ML)☆21Jun 17, 2019Updated 6 years ago
- [CVPR'19] Trust Region Based Adversarial Attack☆20Dec 11, 2020Updated 5 years ago
- DQV-Learning: a novel faster synchronous Deep Reinforcement Learning algorithm☆24Feb 15, 2023Updated 3 years ago
- Generative Model for Neural Networks☆24Jul 2, 2020Updated 5 years ago
- Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019☆47Dec 8, 2022Updated 3 years ago
- [ICML'20] Multi Steepest Descent (MSD) for robustness against the union of multiple perturbation models.☆25Jul 25, 2024Updated last year
- Scaleable input gradient regularization☆22Jul 8, 2019Updated 6 years ago
- Code for Stability Training with Noise (STN)☆22Dec 27, 2020Updated 5 years ago
- ☆25Oct 9, 2022Updated 3 years ago
- Fine-grained ImageNet annotations☆30May 25, 2020Updated 5 years ago
- Implementation of the Biased Boundary Attack for ImageNet☆22Aug 18, 2019Updated 6 years ago
- ☆35May 21, 2025Updated 9 months ago
- Repository of models in Pyro☆30Jul 25, 2024Updated last year
- The differentiable OSQP solver layer for PyTorch☆65Dec 26, 2022Updated 3 years ago
- Analysis of Adversarial Logit Pairing☆60Aug 13, 2018Updated 7 years ago
- OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]☆49Sep 18, 2025Updated 5 months ago
- ☆46May 8, 2024Updated last year
- Code for the paper "Distinguishing the Knowable from the Unknowable with Language Models"☆11Apr 15, 2024Updated last year
- Public code for a paper "Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks."☆35Dec 18, 2018Updated 7 years ago
- This repo contains all the code related to the interactive online Bloch sphere simulator☆18Updated this week
- Scripts for optimization class☆10Mar 16, 2018Updated 7 years ago
- A data processing module implemented with numpy☆10Aug 16, 2022Updated 3 years ago
- Code for experiments on self-prediction as a way to measure introspection in LLMs☆16Dec 10, 2024Updated last year
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆38Jun 14, 2022Updated 3 years ago
- CROWN: A Neural Network Verification Framework for Networks with General Activation Functions☆39Dec 13, 2018Updated 7 years ago
- [NeurIPS 2023] Code for the paper "Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threa…☆39Dec 3, 2024Updated last year