TY - GEN
T1 - Generating traffic-level adversarial examples from feature-level specifications
AU - Flood, Robert
AU - Casadio, Marco
AU - Aspinall, David
AU - Komendantskaya, Ekaterina
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025/4/1
Y1 - 2025/4/1
N2 - 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.
AB - 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.
KW - Adversarial Attacks
KW - Formal Verification
KW - Network Intrusion Detection
UR - https://www.scopus.com/pages/publications/105002716057
U2 - 10.1007/978-3-031-82362-6_8
DO - 10.1007/978-3-031-82362-6_8
M3 - Conference contribution
AN - SCOPUS:105002716057
SN - 9783031823619
T3 - Lecture Notes in Computer Science
SP - 118
EP - 127
BT - Computer Security. ESORICS 2024 International Workshops
A2 - Garcia-Alfaro, Joaquin
A2 - Kalutarage, Harsha
A2 - Yanai, Naoto
A2 - Kozik, Rafał
A2 - Pawlicki, Marek
A2 - Choraś, Michał
A2 - Ksieniewicz, Paweł
A2 - Woźniak, Michał
A2 - Abie, Habtamu
A2 - Pirbhulal, Sandeep
A2 - Ranise, Silvio
A2 - Verderame, Luca
A2 - Cambiaso, Enrico
A2 - Ugarelli, Rita
A2 - Praça, Isabel
A2 - Katt, Basel
A2 - Shukla, Ankur
PB - Springer
T2 - 19th 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
Y2 - 16 September 2024 through 20 September 2024
ER -