Extending XReason: Formal Explanations for Adversarial Detection

Amira Jemaa, Adnan Rashid, Sofiene Tahar
12/31/2024
cs.AIcs.CRcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

Explainable Artificial Intelligence (XAI) plays an important role in improving the transparency and reliability of complex machine learning models, especially in critical domains such as cybersecurity. Despite the prevalence of heuristic interpretation methods such as SHAP and LIME, these techniques often lack formal guarantees and may produce inconsistent local explanations. To fulfill this need, few tools have emerged that use formal methods to provide formal explanations. Among these, XReason uses a SAT solver to generate formal instance-level explanation for XGBoost models. In this paper, we extend the XReason tool to support LightGBM models as well as class-level explanations. Additionally, we implement a mechanism to generate and detect adversarial examples in XReason. We evaluate the efficiency and accuracy of our approach on the CICIDS-2017 dataset, a widely used benchmark for detecting network attacks.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Adversarial attacks and defenses in explainable artificial intelligence: A survey

85% match1 repo3342023

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

84% match2024

eXIAA: eXplainable Injections for Adversarial Attack

83% match2025

Disproving XAI Myths with Formal Methods -- Initial Results

82% match2023

X Hacking: The Threat of Misguided AutoML

82% match1 repo2024

EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods

82% match2024

Cite this paper

@article{jemaa2024extending,
  title  = {Extending XReason: Formal Explanations for Adversarial Detection},
  author = {Amira Jemaa and Adnan Rashid and Sofiene Tahar},
  year   = {2024},
  eprint = {2501.00537},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.00537v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.00537.svg)](https://codeofpaper.com/paper/2501.00537)

Discussion