Black Box

"Black box" refers to systems whose internal workings are opaque, hindering understanding and analysis. Current research focuses on methods to analyze and mitigate the limitations of black-box models, particularly deep neural networks, across diverse applications like code generation, robot design, and autonomous systems. Key approaches involve developing surrogate models, employing novel optimization techniques, and designing explainable AI (XAI) methods to enhance interpretability and trustworthiness. This research is crucial for ensuring the safety, reliability, and fairness of increasingly prevalent AI systems in various fields.

Papers

September 13, 2024

XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution
Kiana Vu, Phung Lai, Truc Nguyen
Black Box Explainable Artificial Intelligence Black Box Model Explanation Model Feature Perturbation

September 5, 2024

In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via Search
Emir Demirović, Christian Schilling, Anna Lukina
Reinforcement Learning Decision Tree Black Box Search Query Tree Specie Neural Network Policy Decision Tree Policy

August 27, 2024

Post-processing fairness with minimal changes
Federico Di Gennaro, Thibault Laugel, Vincent Grari, Xavier Renard, Marcin Detyniecki
Black Box Post Processing Fairness Research Unbiased Prediction Small Change

August 20, 2024

August 17, 2024

ByCAN: Reverse Engineering Controller Area Network (CAN) Messages from Bit to Byte Level
Xiaojie Lin, Baihe Ma, Xu Wang, Guangsheng Yu, Ying He, Ren Ping Liu, Wei Ni
Black Box Reverse Engineering P Bit System Message Controller Area Network Intra Byte

August 13, 2024

Robust Black-box Testing of Deep Neural Networks using Co-Domain Coverage
Aishwarya Gupta, Indranil Saha, Piyush Rai
Deep Neural Network Black Box Fuzz Testing Robust Test Semantic Coverage Stein Coverage

August 12, 2024

August 9, 2024

Axiomatic Characterisations of Sample-based Explainers
Leila Amgoud, Martin C. Cooper, Salim Debbaoui
Line by Line Explanation Black Box Axiomatic Approach Feature Explanation Using Contrasting Concept Abductive Explanation Surrogate Explainers

August 7, 2024

July 31, 2024

Black box meta-learning intrinsic rewards for sparse-reward environments
Octavio Pappalardo, Rodrigo Ramele, Juan Miguel Santos
Meta Learning Black Box Intrinsic Reward Sparse Reward Environment Meta Gradient

July 23, 2024

Learning Instance-Specific Parameters of Black-Box Models Using Differentiable Surrogates
Arnisha Khondaker, Nilanjan Ray
LeArning Abstract Black Box Hyperparameter Optimization Black Box Model Instance Level Differentiable Surrogate

July 19, 2024

July 18, 2024

July 12, 2024

Integrating White and Black Box Techniques for Interpretable Machine Learning
Eric M. Vernon, Naoki Masuyama, Yusuke Nojima
Inherent Interpretability Black Box Interpretable Machine Learning Ensemble Classifier Interpretable Classifier Random Forest Classifier

July 11, 2024

Learning Program Behavioral Models from Synthesized Input-Output Pairs
Tural Mammadov, Dietrich Klakow, Alexander Koller, Andreas Zeller
Black Box Sequence to Sequence Behavior Model Context Free Input Output Pair

Black Box

Papers

XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution

In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via Search

Post-processing fairness with minimal changes

Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders

NoMatterXAI: Generating "No Matter What" Alterfactual Examples for Explaining Black-Box Text Classification Models

ByCAN: Reverse Engineering Controller Area Network (CAN) Messages from Bit to Byte Level

Robust Black-box Testing of Deep Neural Networks using Co-Domain Coverage

Understanding Byzantine Robustness in Federated Learning with A Black-box Server

Peaking into the Black-box: Prediction Intervals Give Insight into Data-driven Quadrotor Model Reliability

Axiomatic Characterisations of Sample-based Explainers

Time is Not Enough: Time-Frequency based Explanation for Time-Series Black-Box Models

Opening the Black Box of 3D Reconstruction Error Analysis with VECTOR

Black box meta-learning intrinsic rewards for sparse-reward environments

Learning Instance-Specific Parameters of Black-Box Models Using Differentiable Surrogates

The Collection of a Human Robot Collaboration Dataset for Cooperative Assembly in Glovebox Environments

FuzzTheREST: An Intelligent Automated Black-box RESTful API Fuzzer

Semantic Prototypes: Enhancing Transparency Without Black Boxes

Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Models

Integrating White and Black Box Techniques for Interpretable Machine Learning

Learning Program Behavioral Models from Synthesized Input-Output Pairs