On the Importance of Domain-specific Explanations in AI-based Cybersecurity Systems (Technical Report)

Paredes, Jose N.; Teze, Juan Carlos L.; Simari, Gerardo I.; Martinez, Maria Vanina

doi:10.48550/arxiv.2108.02006

Cited by 5 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [64] the authors focus on application of XAI in Cybersecurity for specific vertical industry sectors, namely in smart healthcare, smart banking, smart agriculture, smart cities, smart governance etc. Exciting work is [65] where the authors made three contributions: a proposal and discussion of desiderata for the explanation of outputs generated by AI-based Cybersecurity systems; a comparative analysis of approaches in the literature on Explainable Artificial Intelligence (XAI), and a general architecture that can serve as a roadmap for guiding research efforts towards AI-based Cybersecurity systems. In [66] Vigano et al presented Explainable Security (XSec), a new security paradigm that involves several different stakeholders and is multifaceted by nature .…”

Section: Xai Surveys In Cybersecuritymentioning

confidence: 99%

Explainable Artificial Intelligence in CyberSecurity: A Survey

et al. 2022

View full text Add to dashboard Cite

Nowadays, Artificial Intelligence (AI) is widely applied in every area of human being's daily life. Despite the AI benefits, its application suffer from the opacity of complex internal mechanisms and doesn't satisfy by design the principles of Explainable Artificial Intelligence (XAI). The lack of transparency further exacerbates the problem in the field of Cybersecurity because entrusting crucial decisions to a system that cannot explain itself presents obvious dangers. There are several methods in the literature capable of providing explainability of AI results. Anyway, the application of XAI in Cybersecurity can be a doubleedged sword. It substantially improves the Cybersecurity practices but simultaneously leaves the system vulnerable to adversary attacks. Therefore, there is a need to analyze the state-of-the-art of XAI methods in Cybersecurity to provide a clear vision for future research. This study presents an in-depth examination of the application of XAI in Cybersecurity. It considers more than 300 papers to comprehensively analyze the main Cybersecurity application fields, like Intrusion Detection Systems,Malware detection, Phishing and Spam detection, BotNets detection, Fraud detection, Zero-Day vulnerabilities, Digital Forensics and Crypto-Jacking . Specifically, this study focuses on the explainability methods adopted or proposed in these fields, pointing out promising works and new challenges.

show abstract

Section: Xai Surveys In Cybersecuritymentioning

confidence: 99%

Explainable Artificial Intelligence in CyberSecurity: A Survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Another approach was to characterize XAI through its intrinsic properties. Arrieta et al [13] classified XAI models as white box or post hoc models, whereas the authors of [46] and [94] outlined desirable properties for XAI. Hagras [46] discussed the link between humanunderstandable information and the flexibility of the data labeling process.…”

Section: Taxonomymentioning

confidence: 99%

“…Hagras [46] discussed the link between humanunderstandable information and the flexibility of the data labeling process. Paredes et al [94] discussed explanations for cybersecurity and insisted that explanations should be able to capture changes in an attacker's strategy, or to help identify anomalies when they are outlined by detection mechanisms. Kuppa et al [66] proposed a taxonomy for XAI concerning its security properties.…”

Section: Taxonomymentioning

confidence: 99%

Explainable artificial intelligence for cybersecurity: a literature survey

et al. 2022

View full text Add to dashboard Cite

With the extensive application of deep learning (DL) algorithms in recent years, e.g., for detecting Android malware or vulnerable source code, artificial intelligence (AI) and machine learning (ML) are increasingly becoming essential in the development of cybersecurity solutions. However, sharing the same fundamental limitation with other DL application domains, such as computer vision (CV) and natural language processing (NLP), AI-based cybersecurity solutions are incapable of justifying the results (ranging from detection and prediction to reasoning and decision-making) and making them understandable to humans. Consequently, explainable AI (XAI) has emerged as a paramount topic addressing the related challenges of making AI models explainable or interpretable to human users. It is particularly relevant in cybersecurity domain, in that XAI may allow security operators, who are overwhelmed with tens of thousands of security alerts per day (most of which are false positives), to better assess the potential threats and reduce alert fatigue. We conduct an extensive literature review on the intersection between XAI and cybersecurity. Particularly, we investigate the existing literature from two perspectives: the applications of XAI to cybersecurity (e.g., intrusion detection, malware classification), and the security of XAI (e.g., attacks on XAI pipelines, potential countermeasures). We characterize the security of XAI with several security properties that have been discussed in the literature. We also formulate open questions that are either unanswered or insufficiently addressed in the literature, and discuss future directions of research.

show abstract

“…In addition to being able to calculate query probabilities, it is possible to accompany such results with an explanation as to how the system arrived at that answer; explainability was recently identified as a key feature in cybersecurity domains [28]. We discuss two proposals for providing such insights into the kind of results presented in the previous sections.…”

Section: Next Steps: Explainabilitymentioning

confidence: 99%

Argumentation-Based Query Answering under Uncertainty with Application to Cybersecurity

Leiva

García

Shakarian

et al. 2022

BDCC

View full text Add to dashboard Cite

Decision support tools are key components of intelligent sociotechnical systems, and their successful implementation faces a variety of challenges, including the multiplicity of information sources, heterogeneous format, and constant changes. Handling such challenges requires the ability to analyze and process inconsistent and incomplete information with varying degrees of associated uncertainty. Moreover, some domains require the system’s outputs to be explainable and interpretable; an example of this is cyberthreat analysis (CTA) in cybersecurity domains. In this paper, we first present the P-DAQAP system, an extension of a recently developed query-answering platform based on defeasible logic programming (DeLP) that incorporates a probabilistic model and focuses on delivering these capabilities. After discussing the details of its design and implementation, and describing how it can be applied in a CTA use case, we report on the results of an empirical evaluation designed to explore the effectiveness and efficiency of a possible world sampling-based approximate query answering approach that addresses the intractability of exact computations.

show abstract

On the Importance of Domain-specific Explanations in AI-based Cybersecurity Systems (Technical Report)

Cited by 5 publications

References 23 publications

Explainable Artificial Intelligence in CyberSecurity: A Survey

Explainable Artificial Intelligence in CyberSecurity: A Survey

Explainable artificial intelligence for cybersecurity: a literature survey

Argumentation-Based Query Answering under Uncertainty with Application to Cybersecurity

Contact Info

Product

Resources

About