A Fundamental Performance Limitation for Adversarial Classification

03/04/2019
by   Abed AlRahman Al Makdah, et al.
0

Despite the widespread use of machine learning algorithms to solve problems of technological, economic, and social relevance, provable guarantees on the performance of these data-driven algorithms are critically lacking, especially when the data originates from unreliable sources and is transmitted over unprotected and easily accessible channels. In this paper we take an important step to bridge this gap and formally show that, in a quest to optimize their accuracy, binary classification algorithms -- including those based on machine-learning techniques -- inevitably become more sensitive to adversarial manipulation of the data. Further, for a given class of algorithms with the same complexity (i.e., number of classification boundaries), the fundamental tradeoff curve between accuracy and sensitivity depends solely on the statistics of the data, and cannot be improved by tuning the algorithm.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/08/2017

Data-driven Advice for Applying Machine Learning to Bioinformatics Problems

As the bioinformatics field grows, it must keep pace not only with new d...
research
03/27/2017

Multilabel Classification with R Package mlr

We implemented several multilabel classification algorithms in the machi...
research
07/03/2023

Adversarial Learning in Real-World Fraud Detection: Challenges and Perspectives

Data economy relies on data-driven systems and complex machine learning ...
research
03/17/2019

Machine Learning: A Dark Side of Cancer Computing

Cancer analysis and prediction is the utmost important research field fo...
research
07/04/2021

Adaptive calibration for binary classification

This note proposes a way of making probability forecasting rules less se...
research
02/17/2022

Combining Varied Learners for Binary Classification using Stacked Generalization

The Machine Learning has various learning algorithms that are better in ...
research
06/08/2018

Data-driven model for the identification of the rock type at a drilling bit

In order to bridge the gap of more than 15m between the drilling bit and...

Please sign up or login with your details

Forgot password? Click here to reset