Gwinhen / AmI
This repository is for NeurIPS 2018 spotlight paper "Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples."
☆31Updated 2 years ago
Related projects: ⓘ
- code we used in Decision Boundary Analysis of Adversarial Examples https://openreview.net/forum?id=BkpiPMbA-☆27Updated 5 years ago
- Code for the paper "Adversarial Training and Robustness for Multiple Perturbations", NeurIPS 2019☆47Updated last year
- ☆46Updated 3 years ago
- Adversarial Defense for Ensemble Models (ICML 2019)☆60Updated 3 years ago
- Code for AAAI 2018 accepted paper: "Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing the…☆53Updated last year
- A simple implement of an Adversarial Autoencoding ATN(AAE ATN)☆30Updated 7 years ago
- StrAttack, ICLR 2019☆32Updated 5 years ago
- Adversarial Examples on KNN (and its neural network friends)☆19Updated 4 years ago
- Robustness vs Accuracy Survey on ImageNet☆99Updated 3 years ago
- Code for FAB-attack☆31Updated 4 years ago
- Rob-GAN: Generator, Discriminator and Adversarial Attacker☆83Updated 5 years ago
- Detect adversarial images from intermediate features in distance space☆12Updated 6 years ago
- An Algorithm to Quantify Robustness of Recurrent Neural Networks☆46Updated 4 years ago
- ☆11Updated 4 years ago
- AAAI 2019 oral presentation☆49Updated last month
- Improving the Generalization of Adversarial Training with Domain Adaptation☆31Updated 5 years ago
- ☆25Updated 5 years ago
- Code for the unrestricted adversarial examples paper (NeurIPS 2018)☆63Updated 5 years ago
- Interval attacks (adversarial ML)☆21Updated 5 years ago
- NIPS 2017 - Adversarial Learning☆33Updated 6 years ago
- Code for generating adversarial color-shifted images☆19Updated 4 years ago
- ☆18Updated 4 years ago
- Code implementing the experiments described in the NeurIPS 2018 paper "With Friends Like These, Who Needs Adversaries?".☆13Updated 4 years ago
- Code for "Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors"☆61Updated 4 years ago
- Code for Black-Box Adversarial Attack with Transferable Model-based Embedding☆55Updated 4 years ago
- Code for "Diversity can be Transferred: Output Diversification for White- and Black-box Attacks"☆52Updated 3 years ago
- Analysis of Adversarial Logit Pairing☆60Updated 6 years ago
- Code implementation of the paper "With Great Training Comes Great Vulnerability: Practical Attacks against Transfer Learning", at USENIX …☆21Updated 5 years ago
- Code for the paper "MMA Training: Direct Input Space Margin Maximization through Adversarial Training"☆34Updated 4 years ago
- Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation [NeurIPS 2017]☆18Updated 6 years ago