AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical Applications with Categorical Inputs - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical Applications with Categorical Inputs

Résumé

Machine Learning-as-a-Service systems (MLaaS) have been largely developed for cybersecurity-critical applications, such as detecting network intrusions and fake news campaigns. Despite effectiveness, their robustness against adversarial attacks is one of the key trust concerns for MLaaS deployment. We are thus motivated to assess the adversarial robustness of the Machine Learning models residing at the core of these securitycritical applications with categorical inputs. Previous research efforts on accessing model robustness against manipulation of categorical inputs are specific to use cases and heavily depend on domain knowledge, or require white-box access to the target ML model. Such limitations prevent the robustness assessment from being as a domain-agnostic service provided to various real-world applications. We propose a provably optimal yet computationally highly efficient adversarial robustness assessment protocol for a wide band of ML-driven cybersecurity-critical applications. We demonstrate the use of the domain-agnostic robustness assessment method with substantial experimental study on fake news detection and intrusion detection problems.
Fichier principal
Vignette du fichier
IEEEbigdata_Adversarial_Robustness_Assessment_for_Security_Critical_Applications (4).pdf (690.73 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03893496 , version 1 (11-12-2022)

Identifiants

  • HAL Id : hal-03893496 , version 1

Citer

Helene Orsini, Hongyan Bao, Yujun Zhou, Xiangrui Xu, Yufei Han, et al.. AdvCat: Domain-Agnostic Robustness Assessment for Cybersecurity-Critical Applications with Categorical Inputs. BigData 2022 - IEEE International Conference on Big Data, Dec 2022, Osaka, Japan. pp.1-13. ⟨hal-03893496⟩
62 Consultations
48 Téléchargements

Partager

Gmail Facebook X LinkedIn More