EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RAMPART: Reinforcing Autonomous Multi-Agent Protection through Adversarial Resistance in Transportation

Md Tamjid Hossain, Hung La, Shahriar Badsha

ACM Journal on Autonomous Transportation Systems · 2024

DOI: 10.1145/3643137 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Journal on Autonomous Transportation Systems, 2024. Verfasst von Md Tamjid Hossain und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. National Science Foundation, NSF-PFI-TT.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the field of multi-agent autonomous transportation, such as automated payload delivery or highway on-ramp merging, agents routinely exchange knowledge to optimize their shared objective and adapt to environmental novelties through Cooperative Multi-Agent Reinforcement Learning (CMARL) algorithms. This knowledge exchange between agents allows these systems to operate efficiently and adapt to dynamic environments. However, this cooperative learning process is susceptible to adversarial poisoning attacks, as highlighted by contemporary research. Particularly, the poisoning attacks where malicious agents inject deceptive information camouflaged within the differential noise, a pivotal element for differential privacy (DP)-based CMARL algorithms, pose formidable challenges to identify and overcome. The consequences of not addressing this issue are far-reaching, potentially jeopardizing safety-critical operations and the integrity of data privacy in these applications. Existing research has strived to develop anomaly detection based defense models to counteract conventional poisoning methods. Nonetheless, the recurring necessity for model offloading and retraining with labeled anomalous data undermines their practicality, considering the inherently dynamic nature of the safety-critical autonomous transportation applications. Further, it is imperative to maintain data privacy, ensure high performance, and adapt to environmental changes. Motivated by these challenges, this article introduces a novel defense mechanism against stealthy adversarial poisoning attacks in the autonomous transportation domain, termed Reinforcing Autonomous Multi-agent Protection through Adversarial Resistance in Transportation (RAMPART). Leveraging a GAN model at each local node, RAMPART effectively filters out malicious advice in an unsupervised manner while generating synthetic samples for each state-action pair to accommodate environmental uncertainties and eliminate the need for labeled training data. Our extensive experimental analysis, conducted in a private payload delivery network—a common application in the autonomous multi-agent transportation domain—demonstrates that RAMPART successfully defends against a DP-exploited poisoning attack with a 30% attack ratio, achieving an F1 score of 0.852 and accuracy of 96.3% in heavy traffic environments.

Förderung

  • U.S. National Science Foundation
  • NSF-PFI-TT

Zitieren

APA

Hossain, M. T., La, H., & Badsha, S. (2024). RAMPART: Reinforcing Autonomous Multi-Agent Protection through Adversarial Resistance in Transportation. ACM Journal on Autonomous Transportation Systems. https://doi.org/10.1145/3643137

Vancouver

Hossain MT, La H, Badsha S. RAMPART: Reinforcing Autonomous Multi-Agent Protection through Adversarial Resistance in Transportation. ACM Journal on Autonomous Transportation Systems. 2024. doi:10.1145/3643137

BibTeX
@article{Hossain2024,
  author = {Hossain, Md Tamjid and La, Hung and Badsha, Shahriar},
  title = {RAMPART: Reinforcing Autonomous Multi-Agent Protection through Adversarial Resistance in Transportation},
  journal = {ACM Journal on Autonomous Transportation Systems},
  year = {2024},
  doi = {10.1145/3643137}
}
Kostenlos starten →