Software and Tools

Featured Tools

These tools are ready to use for researchers and experienced developers.

Code repository containing data for “CodeLMSec Benchmark: Systematically Evaluating and Finding Security Vulnerabilities in Black-Box Code Language Models”. The paper presents a method to systematically study the security issues of code language models to assess their susceptibility to generating vulnerable code.

Code repository containing data for the paper “Large Language Models for Code: Security Hardening and Adversarial Testing”

MLDoctor is a code base for developers and/or researchers for holistically assessing the risks of inference attacks against machine learning models.

SecML is a python library for Secure and Explainable Machine Learning. It is equipped with evasion and poisoning adversarial machine learning attacks, and it can wrap models and attacks from other different frameworks.

SecML Malware is a python library for creating adversarial attacks against Windows Malware detectors. Built on top of SecML, SecML Malware includes most of the attack proposed in the state of the art.

Code repository containing the implementation for “GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models” (CCS 2020)

Code repository for the paper “ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models”

Repository containing materials for the following paper “Interpretable-through-prototypes deepfake detection for diffusion models.” Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023.

Repository for benchmark paper “Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation” (NeurIPS 2024)

Tracking and documentation of vulnerabilities and exposures of large language models (LVEs).

Code for “CoBo: Collaborative Learning via Bilevel Optimization” published at NeurIPS 2024

Code for “On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists”.

Code for “The Privacy Power of Correlated Noise in Decentralized Learning” Published at ICML 2024.

Repository for differentially private convolutional conditional neural process (DPConvCNP) model presented in the paper Noise-Aware Differentially Private Regression via Meta-Learning (NeurIPS 2024).

Code for: “Private and Collaborative Kaplan- Meier Estimators” published at WPES at CCS 2024.

Code repository containing the implementation for “GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models” (CCS 2020).

Code for: “FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations“ published at PoPETs’24.

Code for: “GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators” published at NeurIPS 2020.

Code for: “ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models” published at USENIX’22.

Code for “MyThisYourThat: Interpretable Identification of Systematic Bias in Federated Learning for Biomedical Images”.

Code for “Personalized Collaborative Fine-Tuning for On-Device Large Language Models” Published at CoLM 2024. Exploration on-device self-supervised collaborative fine-tuning of large language models with limited local data availability, using Low-Rank Adaptation (LoRA).

Code for: “Towards Biologically Plausible and Private Gene Expression Data Generation” published at PoPETs’24.

Code for: “Client-specific Property Inference against Secure Aggregation in Federated Learning” published at WPES at CCS 2023.

Code for: “Client-specific Property Inference against Secure Aggregation in Federated Learning” published at WPES at CCS 2023.

Model and Code for “Meditron-70b: Scaling medical pretraining for large language models”.

This repository with base framework and method for the PFL-DocVQA Competition and code for: “Privacy-Aware Document Visual Question Answering” published in ICDAR 2024.

Code for: “SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models” published at USENIX 2024.

Code and Mathematica notebook for: “Subsampling is not Magic: Why Large Batch Sizes Work for Differentially Private Stochastic Optimisation” (ICML 2024).

Code to reproduce the experiments carried out in “Towards Efficient and Scalable Training of Differentially Private Deep Learning” published at Workshop on Advancing Neural Network Training at International Conference on Machine Learning (WANT@ICML 2024).

The Adversarial Pruning Benchmark is a framework implemented to enable a uniform and reliable evaluation of Adversarial Pruning methods.

AdversarialRecovery is a repository for robust adversarial sample recovery, especially for cross-domain samples (unseen datasets, unseen objects, and unseen adversarial algorithms to the training stage).

This repository provides implementations for training Bayesian Neural Networks (BNNs) using various inference methods, along with comprehensive certifications for their probabilistic robustness, decision robustness, and uncertainty quantification.

The code implements a robustness verification framework for neural networks with general activation functions (e.g., Sigmoid, Tanh), focusing on enhancing the quality of linear bounds in convex relaxation techniques.

The code implements FAST (FeAture SelecTion), a method to enhance the efficiency and effectiveness of test case prioritization for deep neural networks (DNNs).

A Deterministic End-to-End Certification for Training and Inference of Neural Networks.

GeometricKernels is a library that implements kernels — most importantly, heat and Matérn kernels — on non-Euclidean spaces such as Riemannian manifolds, graphs and meshes.

ModSec-AdvLearn is a machine-learning-based methodology that improves the detection of SQL injection attacks on Web Application Firewall (WAF) while addressing vulnerabilities to adversarial manipulations.

Nebula is a tool to perform dynamic analysis of Windows malware which, by generalizing across different behavioral representations and formats, combines diverse information from dynamic log reports.

A general and flexible preimage approximation framework designed to generate inputs that satisfy specific target properties.

SecML-Torch (SecMLT) is an open-source Python library designed to facilitate research in the area of Adversarial Machine Learning (AML) and robustness evaluation.

An open-source Python plugin for the SecML-Torch library that integrates homomorphic encryption techniques within machine learning models.

An open-source Python plugin for the SecML-Torch library that introduces a set of methods for analyzing and mitigating discriminatory bias in machine learning models.

An open-source Python plugin for the SecML-Torch library. This plugin provides tools for the interpretation and explainability of machine learning models.

This tool is the official PyTorch implementation of the σ-zero: Gradient-based Optimization of L0-norm Adversarial Examples.

TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a simple linear probe-based method and a more sophisticated metric learning method to achieve this. The project also releases the computationally expensive activation data to stimulate further AI safety research.

The Uncertainty Adversarial Robustness repository provides practical tools for performing uncertainty attacks against robust models.

This project leverages a novel metric for measuring the tightness of IBP bounds.