Bridging the Explanation Gap in AI Security: A Task-Driven Approach to XAI Methods Evaluation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00373606" target="_blank" >RIV/68407700:21230/24:00373606 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.5220/0012475200003636" target="_blank" >https://doi.org/10.5220/0012475200003636</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5220/0012475200003636" target="_blank" >10.5220/0012475200003636</a>

Result language

angličtina

Original language name

Bridging the Explanation Gap in AI Security: A Task-Driven Approach to XAI Methods Evaluation

Original language description

Deciding which XAI technique is best depends not only on the domain, but also on the given task, the dataset used, the model being explained, and the target goal of that model. We argue that the evaluation of XAI methods has not been thoroughly analyzed in the network security domain, which presents a unique type of challenge. While there are XAI methods applied in network security there is still a large gap between the needs of security stakeholders and the selection of the optimal method. We propose to approach the problem by first defining the stack-holders in security and their prototypical tasks. Each task defines inputs and specific needs for explanations. Based on these explanation needs (e.g. understanding the performance, or stealing a model), we created five XAI evaluation techniques that are used to compare and select which XAI method is best for each task (dataset, model, and goal). Our proposed approach was evaluated by running experiments for different security stakehol ders, machine learning models, and XAI methods. Results were compared with the AutoXAI technique and random selection. Results show that our proposal to evaluate and select XAI methods for network security is well-grounded and that it can help AI security practitioners find better explanations for their given tasks.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/VJ02010020" target="_blank" >VJ02010020: AI-Dojo: Multiagent Testbed for Research and Testing of AI-driven Cybersecurity Technologies</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 16th International Conference on Agents and Artificial Intelligence (Volume 3)

ISBN

978-989-758-680-4

ISSN

2184-3589

e-ISSN

2184-433X

Number of pages

8

Pages from-to

1370-1377

Publisher name

Science and Technology Publications, Lda

Place of publication

Setúbal

Event location

Rome

Event date

Feb 24, 2024

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—