ryderling / DEEPSEC
DEEPSEC: A Uniform Platform for Security Analysis of Deep Learning Model
☆213Updated 5 years ago
Alternatives and similar repositories for DEEPSEC:
Users that are interested in DEEPSEC are comparing it to the libraries listed below
- Trojan Attack on Neural Network☆183Updated 3 years ago
- Benchmarking and Visualization Tool for Adversarial Machine Learning☆188Updated last year
- Code implementation of the paper "Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks", at IEEE Security and P…☆280Updated 5 years ago
- 机器学习安全相关论文、代码☆41Updated 5 years ago
- TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classifica…☆290Updated 7 months ago
- Attacking a dog vs fish classification that uses transfer learning inceptionV3☆70Updated 6 years ago
- MagNet: a Two-Pronged Defense against Adversarial Examples☆98Updated 6 years ago
- ☆92Updated 4 years ago
- ☆143Updated 5 months ago
- ☆79Updated 5 years ago
- ☆18Updated 2 years ago
- This is for releasing the source code of the ACSAC paper "STRIP: A Defence Against Trojan Attacks on Deep Neural Networks"☆55Updated 4 months ago
- 对抗样本(Adversarial Examples)和 投毒攻击(Poisoning Attacks)相关资料☆115Updated 5 years ago
- ☆64Updated 5 years ago
- A unified benchmark problem for data poisoning attacks☆153Updated last year
- A repository to quickly generate synthetic data and associated trojaned deep learning models☆77Updated last year
- ☆83Updated 4 years ago
- Detecting Adversarial Examples in Deep Neural Networks☆66Updated 7 years ago
- ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation☆50Updated 2 years ago
- This repo keeps track of popular provable training and verification approaches towards robust neural networks, including leaderboards on …☆99Updated 2 years ago
- Knockoff Nets: Stealing Functionality of Black-Box Models☆94Updated 2 years ago
- Code for ICML 2019 paper "Simple Black-box Adversarial Attacks"☆197Updated 2 years ago
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (RAID 2018)☆48Updated 6 years ago
- Implementation of the Boundary Attack algorithm as described in Brendel, Wieland, Jonas Rauber, and Matthias Bethge. "Decision-Based Adve…☆94Updated 4 years ago
- Official Repository for the AAAI-20 paper "Hidden Trigger Backdoor Attacks"☆124Updated last year
- Simple PyTorch implementations of Badnets on MNIST and CIFAR10.☆170Updated 2 years ago
- Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models (published in ICLR2018)☆239Updated 5 years ago
- This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks…☆122Updated 3 years ago
- Code for ML Doctor☆88Updated 7 months ago
- ☆84Updated last year