Free access to article on the security of machine learning

News

  • Author: Statistics Views
  • Date: 24 September 2018

Each week, we select a recently published article and provide free access. This week's is from WIREs Data Mining and Knowledge Discovery and is available from the May/June 2018 issue.

A dynamic‐adversarial mining approach to the security of machine learning

Tegjyot Singh, Sethi Mehmed Kantardzic, Lingyu Lyu and Jiashun Chen

WIREs Data Mining and Knowledge Discovery, Vol. 8, Issue 3, May/June 2018, e1245

https://doi.org/10.1002/widm.1245

thumbnail image: Free access to article on the security of machine learning

Operating in a dynamic real‐world environment requires a forward thinking and adversarial aware design for classifiers beyond fitting the model to the training data. In such scenarios, it is necessary to make classifiers such that they are: (a) harder to evade, (b) easier to detect changes in the data distribution over time, and (c) be able to retrain and recover from model degradation. While most works in the security of machine learning have concentrated on the evasion resistance problem (a), there is little work in the areas of reacting to attacks (b) and (c). Additionally, while streaming data research concentrates on the ability to react to changes to the data distribution, they often take an adversarial agnostic view of the security problem. This makes them vulnerable to adversarial activity, which is aimed toward evading the concept drift detection mechanism itself. In this paper, we analyze the security of machine learning from a dynamic and adversarial aware perspective. The existing techniques of restrictive one‐class classifier models, complex learning‐based ensemble models, and randomization‐based ensemble models are shown to be myopic as they approach security as a static task. These methodologies are ill suited for a dynamic environment, as they leak excessive information to an adversary who can subsequently launch attacks which are indistinguishable from the benign data. Based on empirical vulnerability analysis against a sophisticated adversary, a novel feature importance hiding approach for classifier design is proposed. The proposed design ensures that future attacks on classifiers can be detected and recovered from. The proposed work provides motivation, by serving as a blueprint, for future work in the area of dynamic‐adversarial mining, which combines lessons learned from streaming data mining, adversarial learning, and cybersecurity.

Related Topics

Related Publications

Related Content

Site Footer

Address:

This website is provided by John Wiley & Sons Limited, The Atrium, Southern Gate, Chichester, West Sussex PO19 8SQ (Company No: 00641132, VAT No: 376766987)

Published features on StatisticsViews.com are checked for statistical accuracy by a panel from the European Network for Business and Industrial Statistics (ENBIS)   to whom Wiley and StatisticsViews.com express their gratitude. This panel are: Ron Kenett, David Steinberg, Shirley Coleman, Irena Ograjenšek, Fabrizio Ruggeri, Rainer Göb, Philippe Castagliola, Xavier Tort-Martorell, Bart De Ketelaere, Antonio Pievatolo, Martina Vandebroek, Lance Mitchell, Gilbert Saporta, Helmut Waldl and Stelios Psarakis.