arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.02256cs.LGcs.AIcs.MAstat.ML
收藏

多学习者的对抗回归

Adversarial Regression with Multiple Learners

Vanderbilt University(范德堡大学);Amherst College(阿默斯特学院)

Liang Tong, Sixie Yu, Scott Alfeld, Yevgeniy Vorobeychik

摘要:

尽管机器学习技术在实践中取得了相当大的成功,但许多研究表明,许多方法容易受到攻击。此类攻击的一个重要类别涉及攻击者在测试时更改功能以导致错误的预测。以前对这个问题的研究让一个学习者与一个对手对抗。然而,在许多情况下,对手的决定是针对一个学习者的集合,而不是专门针对每个独立的。我们研究了多个学习者的对抗线性回归问题。我们近似产生的游戏,表现出上界的学习损失函数,并表明,产生的游戏有一个独特的对称均衡。我们提出了一个算法来计算这个平衡,并通过大量的实验表明,平衡模型是显着更强大的比传统的正则化线性回归。

英文摘要:

Despite the considerable success enjoyed by machine learning techniques in practice, numerous studies demonstrated that many approaches are vulnerable to attacks. An important class of such attacks involves adversaries changing features at test time to cause incorrect predictions. Previous investigations of this problem pit a single learner against an adversary. However, in many situations an adversary's decision is aimed at a collection of learners, rather than specifically targeted at each independently. We study the problem of adversarial linear regression with multiple learners. We approximate the resulting game by exhibiting an upper bound on learner loss functions, and show that the resulting game has a unique symmetric equilibrium. We present an algorithm for computing this equilibrium, and show through extensive experiments that equilibrium models are significantly more robust than conventional regularized linear regression.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑