Generating traffic-level adversarial examples from feature-level specifications

Robert Flood*, Marco Casadio, David Aspinall, Ekaterina Komendantskaya

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Machine learning-based network intrusion detection methods often rely on statistical summaries of traffic, causing a disconnect between the traffic space and the feature space that is difficult to bridge [13]. Realistic adversarial attacks are hard to generate because natural well-formedness constraints at the traffic level aren’t respected at the feature level with usual adversarial attack generation methods. We use a novel attack generation method combining two tools: (1) a bespoke synthetic traffic generation suite, PackGen, and (2) a formal verification tool for neural networks, Vehicle [7]. PackGen produces aggregated Markov chain representations of network traffic which allows us to reconstruct valid packet sequences that are modified by realistic perturbations on an input specification. Vehicle’s formal specification language lets us represent granular threat models such as adversaries who can only manipulate packet timings. Unlike other methods, Vehicle’s formal verification is guaranteed to find counterexamples if they exist, which correspond with evasive adversarial examples. We feed these feature-level counterexamples into modified PackGen representations to generate PCAP files containing reconstructed, evasive network flows, generating adversarial examples that cross the gap between the traffic and feature spaces. We evaluate PackGen by replicating DoS traffic using a variety of timing distributions, before testing our full pipeline by producing evasive counterexamples, outperforming projected gradient descent.

Original languageEnglish
Title of host publicationComputer Security. ESORICS 2024 International Workshops
EditorsJoaquin Garcia-Alfaro, Harsha Kalutarage, Naoto Yanai, Rafał Kozik, Marek Pawlicki, Michał Choraś, Paweł Ksieniewicz, Michał Woźniak, Habtamu Abie, Sandeep Pirbhulal, Silvio Ranise, Luca Verderame, Enrico Cambiaso, Rita Ugarelli, Isabel Praça, Basel Katt, Ankur Shukla
PublisherSpringer
Pages118-127
Number of pages10
ISBN (Print)9783031823619
DOIs
Publication statusPublished - 1 Apr 2025
Event19th International Workshop on Data Privacy Management, DPM 2024, 8th International Workshop on Cryptocurrencies and Blockchain Technology, CBT 2024 and 10th Workshop on the Security of Industrial Control Systems and of Cyber-Physical Systems, CyberICPS 2024 which were held in conjunction with the 29th European Symposium on Research in Computer Security, ESORICS 2024 - Bydgoszcz, Poland
Duration: 16 Sept 202420 Sept 2024

Publication series

NameLecture Notes in Computer Science
Volume15264 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference19th International Workshop on Data Privacy Management, DPM 2024, 8th International Workshop on Cryptocurrencies and Blockchain Technology, CBT 2024 and 10th Workshop on the Security of Industrial Control Systems and of Cyber-Physical Systems, CyberICPS 2024 which were held in conjunction with the 29th European Symposium on Research in Computer Security, ESORICS 2024
Country/TerritoryPoland
CityBydgoszcz
Period16/09/2420/09/24

Keywords / Materials (for Non-textual outputs)

  • Adversarial Attacks
  • Formal Verification
  • Network Intrusion Detection

Fingerprint

Dive into the research topics of 'Generating traffic-level adversarial examples from feature-level specifications'. Together they form a unique fingerprint.

Cite this