English
Related papers

Related papers: XMutant: XAI-based Fuzzing for Deep Learning Syste…

200 papers

The increasing complexity of machine learning models in computer vision, particularly in face verification, requires the development of explainable artificial intelligence (XAI) to enhance interpretability and transparency. This study…

Computer Vision and Pattern Recognition · Computer Science 2025-01-13 Miriam Doh , Caroline Mazini Rodrigues , N. Boutry , L. Najman , Matei Mancas , Bernard Gosselin

Fuzzing is a widely used technique for detecting software bugs and vulnerabilities. Most popular fuzzers generate new inputs using an evolutionary search to maximize code coverage. Essentially, these fuzzers start with a set of seed inputs,…

Software Engineering · Computer Science 2020-09-14 Dongdong She , Rahul Krishna , Lu Yan , Suman Jana , Baishakhi Ray

Deep learning models are one of the security strategies, trained on extensive datasets, and play a critical role in detecting and responding to these threats by recognizing complex patterns in malicious code. However, the opaque nature of…

Cryptography and Security · Computer Science 2025-08-15 Richa Dasila , Vatsala Upadhyay , Samo Bobek , Abhishek Vaish

Many explainable AI (XAI) techniques strive for interpretability by providing concise salient information, such as sparse linear factors. However, users either only see inaccurate global explanations, or highly-varying local explanations.…

Human-Computer Interaction · Computer Science 2024-04-11 Jessica Y. Bo , Pan Hao , Brian Y. Lim

Machine learning models are notoriously difficult to interpret and debug. This is particularly true of neural networks. In this work, we introduce automated software testing techniques for neural networks that are well-suited to discovering…

Machine Learning · Statistics 2018-07-31 Augustus Odena , Ian Goodfellow

While AI-coding assistants accelerate software development, current testing frameworks struggle to keep pace with the resulting volume of AI-generated code. Traditional fuzzing techniques often allocate resources uniformly and lack semantic…

Software Engineering · Computer Science 2026-02-13 Ziyi Yang , Kalit Inani , Keshav Kabra , Vima Gupta , Anand Padmanabha Iyer

The problem of revealing botnet activity through Domain Generation Algorithm (DGA) detection seems to be solved, considering that available deep learning classifiers achieve accuracies of over 99.9%. However, these classifiers provide a…

Cryptography and Security · Computer Science 2023-09-26 Arthur Drichel , Ulrike Meyer

Fuzz testing is a fundamental technique employed to identify vulnerabilities within software systems. However, the process can be protracted and resource-intensive, especially when confronted with extensive codebases. In this work, I…

Software Engineering · Computer Science 2024-12-12 Saket Upadhyay

Learning from Demonstration (LfD) is a powerful type of machine learning that can allow novices to teach and program robots to complete various tasks. However, the learning process for these systems may still be difficult for novices to…

Robotics · Computer Science 2024-10-11 Morris Gu , Elizabeth Croft , Dana Kulic

Generating valid test inputs for a program is much easier if one knows the input language. We present first successes for a technique that, given a program P without any input samples or models, learns an input grammar that represents the…

Software Engineering · Computer Science 2018-10-22 Rahul Gopinath , Björn Mathis , Mathias Höschele , Alexander Kampmann , Andreas Zeller

Explainable Artificial Intelligence (XAI) aims to provide insights into the decision-making process of AI models, allowing users to understand their results beyond their decisions. A significant goal of XAI is to improve the performance of…

Artificial Intelligence · Computer Science 2023-06-12 Andrea Apicella , Luca Di Lorenzo , Francesco Isgrò , Andrea Pollastro , Roberto Prevete

The main objective of this paper is to develop a new semantic Network structure, based on the fuzzy sets theory, used in Artificial Intelligent system in order to provide effective on-line assistance to users of new technological systems.…

Artificial Intelligence · Computer Science 2012-06-07 Mohamed Nazih Omri , Mohamed Ali Mahjoub

MLIR (Multi-Level Intermediate Representation) has rapidly become a foundational technology for modern compiler frameworks, enabling extensibility across diverse domains. However, ensuring the correctness and robustness of MLIR itself…

Software Engineering · Computer Science 2025-10-10 Zeyu Sun , Jingjing Liang , Weiyi Wang , Chenyao Suo , Junjie Chen , Fanjiang Xu

We introduce a novel methodology for identifying adversarial attacks on deepfake detectors using eXplainable Artificial Intelligence (XAI). In an era characterized by digital advancement, deepfakes have emerged as a potent tool, creating a…

Cryptography and Security · Computer Science 2024-08-20 Ben Pinhasov , Raz Lapid , Rony Ohayon , Moshe Sipper , Yehudit Aperstein

Compiler technologies in deep learning and domain-specific hardware acceleration are increasingly adopting extensible compiler frameworks such as Multi-Level Intermediate Representation (MLIR) to facilitate more efficient development. With…

Software Engineering · Computer Science 2024-08-28 Ben Limpanukorn , Jiyuan Wang , Hong Jin Kang , Eric Zitong Zhou , Miryung Kim

Nowadays, quantum program is widely used and quickly developed. However, the absence of testing methodology restricts their quality. Different input format and operator from traditional program make this issue hard to resolve. In this…

Software Engineering · Computer Science 2018-10-25 Jiyuan Wang , Ming Gao , Yu Jiang , Jianguang Lou , Yue Gao , Dongmei Zhang , Jiaguang Sun

Mutants support testing and debugging in two roles: (i) as test goals and (ii) as substitutes for real faults. Hard-to-kill mutants provide better guidance for test improvement, while realism is essential when mutants are used to simulate…

Software Engineering · Computer Science 2026-04-27 Zaheed Ahmed , Emmanuel Charleson Dapaah , Philip Makedonski , Jens Grabowski

Explainable AI (XAI) has emerged as a powerful tool for improving the performance of AI models, going beyond providing model transparency and interpretability. The scarcity of labeled data remains a fundamental challenge in developing…

Computation and Language · Computer Science 2025-06-05 Melkamu Abay Mersha , Mesay Gemeda Yigezu , Atnafu Lambebo Tonja , Hassan Shakil , Samer Iskander , Olga Kolesnikova , Jugal Kalita

Explainable artificial intelligence (XAI) methods lack ground truth. In its place, method developers have relied on axioms to determine desirable properties for their explanations' behavior. For high stakes uses of machine learning that…

Machine Learning · Computer Science 2022-09-02 Isha Hameed , Samuel Sharpe , Daniel Barcklow , Justin Au-Yeung , Sahil Verma , Jocelyn Huang , Brian Barr , C. Bayan Bruss

Interpretability of Deep Learning (DL) is a barrier to trustworthy AI. Despite great efforts made by the Explainable AI (XAI) community, explanations lack robustness -- indistinguishable input perturbations may lead to different XAI…

Machine Learning · Computer Science 2023-08-01 Wei Huang , Xingyu Zhao , Gaojie Jin , Xiaowei Huang