论文标题
为基于枢纽的对抗攻击辩护音乐推荐人
Defending a Music Recommender Against Hubness-Based Adversarial Attacks
论文作者
论文摘要
对抗性攻击会大大降低推荐人和其他机器学习系统的性能，从而增加对防御机制的需求。我们提出了针对攻击的新防御线，这些攻击利用了在高维数据空间（所谓的中心问题）中运行的推荐人的脆弱性。我们使用一种全球数据缩放方法，即相互接近（MP）来捍卫现实世界中的推荐人，该音乐以前易受攻击，这些攻击夸大了推荐特定歌曲的次数。我们发现，将MP用作防御会大大提高推荐人对一系列攻击的鲁棒性，成功的攻击率约为44％（在防守之前）下降到不到6％（防守后）。此外，仍然能够以明显降低音频质量的价格来欺骗卫冕系统的对抗性例子，如平均SNR降低所示。
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.
