ECML PKDD 2018 Workshops

Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an indiscriminate way. Label flipping attacks are a special case of data poisoning, where the attacker can control the labels assigned to a fraction of the training points. Even if the capabilities of the attacker are constrained, these attacks have been shown to be effective to significantly degrade the performance of the system. In this paper we propose an efficient algorithm to perform optimal label flipping poisoning attacks and a mechanism to detect and relabel suspicious data points, mitigating the effect of such poisoning attacks.

[1]  David W. Coit,et al.  Multi-objective optimization using genetic algorithms: A tutorial , 2006, Reliab. Eng. Syst. Saf..

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[4]  Kalyanmoy Deb,et al.  Muiltiobjective Optimization Using Nondominated Sorting in Genetic Algorithms , 1994, Evolutionary Computation.

[5]  S. N. Singh,et al.  A comprehensive survey on multi-objective evolutionary optimization in power system applications , 2010, IEEE PES General Meeting.

[6]  T. Freund,et al.  Strategies for Reducing Potentially Avoidable Hospitalizations for Ambulatory Care–Sensitive Conditions , 2013, The Annals of Family Medicine.

[7]  Alenka Poplin.  Digital Serious Game for Urban Planning: “B3—Design Your Marketplace!” , 2014 .

[8]  Eric Rollins,et al.  Medicare-Medicaid eligible beneficiaries and potentially avoidable hospitalizations. , 2014, Medicare & medicaid research review.

[9]  Joshua B. Tenenbaum,et al.  Building machines that learn and think like people , 2016, Behavioral and Brain Sciences.

[10]  Ernest Davis,et al.  Commonsense reasoning and commonsense knowledge in artificial intelligence , 2015, Commun. ACM.

[11]  A. Stewart,et al.  Preventable hospitalizations and access to health care. , 1995, JAMA.

[12]  Vera Georgescu,et al.  Geographic variation in potentially avoidable hospitalizations in France. , 2015, Health affairs.

[13]  Gary G. Yen,et al.  Performance Metric Ensemble for Multiobjective Evolutionary Algorithms , 2014, IEEE Transactions on Evolutionary Computation.

[14]  Jing J. Liang,et al.  A survey on multi-objective evolutionary algorithms for the solution of the environmental/economic dispatch problems , 2018, Swarm Evol. Comput..

[15]  Qiang Yang,et al.  Lifelong Machine Learning Systems: Beyond Learning Algorithms , 2013, AAAI Spring Symposium: Lifelong Machine Learning.

[16]  Theodore B. Trafalis,et al.  Support vector machine for regression and applications to financial forecasting , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[17]  Soroosh Sorooshian,et al.  Multi-objective global optimization for hydrologic models , 1998 .

[18]  V. Vapnik.  Pattern recognition using generalized portrait method , 1963 .

[19]  Claudia Eckert,et al.  Support vector machines under adversarial label contamination , 2015, Neurocomputing.

[20]  Alberto D. Pascual-Montano,et al.  A survey of dimensionality reduction techniques , 2014, ArXiv.

[21]  Daniel Neagu,et al.  Interpreting random forest models using a feature contribution method , 2013, 2013 IEEE 14th International Conference on Information Reuse & Integration (IRI).

[22]  Gilles Louppe,et al.  Understanding variable importances in forests of randomized trees , 2013, NIPS.

[23]  Jean-Marie Robine,et al.  Comparison of two methods to report potentially avoidable hospitalizations in France in 2012: a cross-sectional study , 2015, BMC Health Services Research.

[24]  Claudia Eckert,et al.  Adversarial Label Flips Attack on Support Vector Machines , 2012, ECAI.

[25]  Marco Laumanns,et al.  SPEA2: Improving the strength pareto evolutionary algorithm , 2001 .

[26]  Eileen Moran,et al.  Predicting Potentially Avoidable Hospitalizations , 2014, Medical care.