pralab / secml-torch
SecML-Torch: A Library for Robustness Evaluation of Deep Learning Models
☆49Updated last month
Alternatives and similar repositories for secml-torch:
Users that are interested in secml-torch are comparing it to the libraries listed below
- A Python library for Secure and Explainable Machine Learning☆175Updated 3 months ago
- Code for the paper Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers☆58Updated 2 years ago
- This repository contains code and data of the paper **On the Limitations of Continual Learning for Malware Classification**, accepted to …☆17Updated last year
- Attack benchmark repository☆14Updated last week
- A curated list of academic events on AI Security & Privacy☆148Updated 8 months ago
- Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples☆19Updated 2 years ago
- Code for "On Adaptive Attacks to Adversarial Example Defenses"☆87Updated 4 years ago
- Code for the AsiaCCS 2021 paper: "Malware makeover: Breaking ML-based static analysis by modifying executable bytes"☆51Updated 11 months ago
- deep learning, malware detection, predictive uncertainty, dataset shift, calibration, uncertainty quantification, android malware☆15Updated 3 years ago
- DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness (ICLR 2024)☆14Updated last year
- PhD/MSc course on Machine Learning Security (Univ. Cagliari)☆209Updated 4 months ago
- ☆64Updated 4 years ago
- Source code for the Energy-Latency Attacks via Sponge Poisoning paper.☆15Updated 3 years ago
- ☆22Updated last year
- Foolbox implementation for NeurIPS 2021 Paper: "Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints".☆25Updated 3 years ago
- Security evaluation module with onnx, pytorch, and SecML.☆13Updated 3 years ago
- ☆18Updated 2 years ago
- Attacking a dog vs fish classification that uses transfer learning inceptionV3☆70Updated 7 years ago
- Code library for the Tesseract framework from 'TESSERACT: Eliminating experimental bias in malware classification across space and time'☆12Updated 4 months ago
- A repository to quickly generate synthetic data and associated trojaned deep learning models☆77Updated last year
- Create adversarial attacks against machine learning Windows malware detectors☆218Updated last week
- Implementation of the paper "MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation".☆30Updated 3 years ago
- Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (ICLR '20)☆30Updated 4 years ago
- Code for the paper: Label-Only Membership Inference Attacks☆65Updated 3 years ago
- This repository provides simple PyTorch implementations for adversarial training methods on CIFAR-10.☆165Updated 4 years ago
- Applying backdoor attacks to BadNet on MNIST and ResNet on CIFAR10.☆11Updated 3 years ago
- Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (RAID 2018)☆48Updated 6 years ago
- ☆144Updated 6 months ago
- Code Implementation for Traceback of Data Poisoning Attacks in Neural Networks☆19Updated 2 years ago
- adversarial malware detection via a principled way☆20Updated last year