moDel Agnostic Language for Exploration and eXplanation

An automatic obfuscation tool for Android apps that works in a black-box fashion, supports advanced obfuscation features and has a modular architecture easily extensible with new techniques

A Python module for parallel optimization of expensive black-box functions

code for our CVPR 2022 paper "DINE: Domain Adaptation from Single and Multiple Black-box Predictors"

Simplicial Homology Global Optimization

Causal Responsibility EXplanations for Image Classifiers and Tabular Data

[EMNLP'24] MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning

[NeurIPS'20] Learning Black-Box Attackers with Transferable Priors and Query Feedback

Black-box Few-shot Knowledge Distillation

Model explanation provides the ability to interpret the effect of the predictors on the composition of an individual score.

Retrospective Extraction of Visual and Logical Insights for Ontology-based interpretation of Neural Networks

Bootplot is a package for black-box uncertainty visualization.

AI Explanation methods based on coalitional game theory, to explain any machine learning prediction.

Togomori is a comprehensive solution for web applications reconnaissance designed to simplify the process of information gathering and data visualization.

Pytorch Implementation of SemiAdv.

A Python implementation of a Genetic Algorithm designed to solve a black-box optimization problem.

Research on Material Science using Neural Networks black box approach

Black-box testing using Equivalence Partitioning (EP) and Boundary Value Analysis (BVA).

A reference implementation of non-functional black-box performance benchmarking ⚫ for ROS 2

System 2 Reasoning for LLMs. An inference-time Supervisor Kernel that forces verification before generation to mitigate hallucinations. "Latency is the price of Integrity."