(Self) Driving Under the Influence: Intoxicating Adversarial Network Inputs
Abstract
Traditional network control planes can be slow and require manual tinkering from operators to change their behavior. There is thus great interest in a faster, data-driven approach that uses signals from real-time traffic instead. However, the promise of fast and automatic reaction to data comes with new risks: malicious inputs designed towards negative outcomes for the network, service providers, users, and operators.
Adversarial inputs are a well-recognized problem in other areas; we show that networking applications are susceptible to them too. We characterize the attack surface of data-driven networks and examine how attackers with different privileges—from infected hosts to operator-level access—may target network infrastructure, applications, and protocols. To illustrate the problem, we present case studies with concrete attacks on recently proposed data-driven systems.
Our analysis urgently calls for a careful study of attacks and defenses in data-driven networking, with a view towards ensuring that their promise is not marred by oversights in robust design.
People
BibTex
@INPROCEEDINGS{meier2019driving,
isbn = {978-1-4503-7020-2},
doi = {10.1145/3365609.3365850},
year = {2019},
booktitle = {Proceedings of the 18th ACM Workshop on Hot Topics in Networks (HotNets '19)},
type = {Conference Paper},
author = {Meier, Roland and Holterbach, Thomas and Keck, Stephan and Stähli, Matthias and Lenders, Vincent and Singla, Ankit and Vanbever, Laurent},
language = {en},
address = {New York, NY},
publisher = {Association for Computing Machinery},
title = {(Self) Driving Under the Influence: Intoxicating Adversarial Network Inputs},
PAGES = {34 - 42},
Note = {18th ACM Workshop on Hot Topics in Networks (HotNets 2019); Conference Location: Princeton, NJ, USA; Conference Date: November 13-15, 2019}
}Research Collection: 20.500.11850/384537