Defending a Music Recommender Against Hubness-Based Adversarial Attacks
This addresses a specific vulnerability in high-dimensional recommender systems, offering a practical defence mechanism for music recommendation applications.
The paper tackles the problem of defending a music recommender against hubness-based adversarial attacks by using Mutual Proximity scaling, which reduces attack success rates from around 44% to less than 6% and degrades audio quality of adversarial examples.
Adversarial attacks can drastically degrade performance of recommenders and other machine learning systems, resulting in an increased demand for defence mechanisms. We present a new line of defence against attacks which exploit a vulnerability of recommenders that operate in high dimensional data spaces (the so-called hubness problem). We use a global data scaling method, namely Mutual Proximity (MP), to defend a real-world music recommender which previously was susceptible to attacks that inflated the number of times a particular song was recommended. We find that using MP as a defence greatly increases robustness of the recommender against a range of attacks, with success rates of attacks around 44% (before defence) dropping to less than 6% (after defence). Additionally, adversarial examples still able to fool the defended system do so at the price of noticeably lower audio quality as shown by a decreased average SNR.