(Self) Driving Under the Influence: Intoxicating Adversarial Network Inputs

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 datadriven 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.