Adversarial attacks on Copyright Detection Systems
This highlights a security threat for copyright enforcement on the web, though it is incremental as it applies known adversarial attack methods to a new domain.
The paper demonstrates that industrial copyright detection systems, particularly neural network-based ones, are vulnerable to adversarial attacks, where simple gradient methods can create adversarial music that successfully fools systems like AudioTag and YouTube's Content ID.
It is well-known that many machine learning models are susceptible to adversarial attacks, in which an attacker evades a classifier by making small perturbations to inputs. This paper discusses how industrial copyright detection tools, which serve a central role on the web, are susceptible to adversarial attacks. We discuss a range of copyright detection systems, and why they are particularly vulnerable to attacks. These vulnerabilities are especially apparent for neural network based systems. As a proof of concept, we describe a well-known music identification method, and implement this system in the form of a neural net. We then attack this system using simple gradient methods. Adversarial music created this way successfully fools industrial systems, including the AudioTag copyright detector and YouTube's Content ID system. Our goal is to raise awareness of the threats posed by adversarial examples in this space, and to highlight the importance of hardening copyright detection systems to attacks.