Machine Learning For Security: The Case of Side-Channel Attack Detection at Run-time

Maria Mushtaq 1 Ayaz Akram 2 Muhammad Khurram Bhatti Maham Chaudhry Muneeb Yousaf Umer Farooq Vianney Lapotre 3 Guy Gogniat 4
1 Lab-STICC_UBS_CACS_MOCS
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
3 Lab-STICC_UBS_CACS_MOCS
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : This paper presents experimental evaluation and comparative analysis on the use of various Machine Learning (ML) models for detecting Cache-based Side Channel Attacks (CSCAs) in Intel's x86 architecture. The paper provides performance evaluation of ML models based on run-time detection accuracy, speed, computational overhead, and distribution of error in terms of false positives and false negatives. Experiments are performed using state-of-the-art CSCAs namely; Flush+Reload and Flush+Flush attacks, under realistic load conditions on RSA and AES crypto-systems. The paper provides quantitative & qualitative analysis of at least 12 ML models being used for CSCA detection for the first time.
Type de document :
Communication dans un congrès
ICECS-2018, Dec 2018, Bordeaux, France
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01876792
Contributeur : Maria Mushtaq <>
Soumis le : mardi 18 septembre 2018 - 18:39:43
Dernière modification le : samedi 6 octobre 2018 - 00:08:14

Fichier

ICECS_2018 (4).pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01876792, version 1

Citation

Maria Mushtaq, Ayaz Akram, Muhammad Khurram Bhatti, Maham Chaudhry, Muneeb Yousaf, et al.. Machine Learning For Security: The Case of Side-Channel Attack Detection at Run-time. ICECS-2018, Dec 2018, Bordeaux, France. 〈hal-01876792〉

Partager

Métriques

Consultations de la notice

161

Téléchargements de fichiers

89