Machine Learning: A Dark Side of Cancer Computing

TL;DR

This paper exposes the potential for unethical manipulation of machine learning algorithms in cancer prediction, demonstrating how accuracy can be artificially inflated to 100% on the Wisconsin dataset through exploitative methods.

Contribution

It reveals the vulnerabilities of machine learning algorithms in cancer analysis and highlights the ethical concerns and potential for misleading results in current research.

Findings

Machine learning can achieve 100% accuracy through unethical data manipulation.

Current accuracy claims may be misleading and not reflect true model performance.

The paper emphasizes the importance of validating the correctness of accuracy metrics.

Abstract

Cancer analysis and prediction is the utmost important research field for well-being of humankind. The Cancer data are analyzed and predicted using machine learning algorithms. Most of the researcher claims the accuracy of the predicted results within 99%. However, we show that machine learning algorithms can easily predict with an accuracy of 100% on Wisconsin Diagnostic Breast Cancer dataset. We show that the method of gaining accuracy is an unethical approach that we can easily mislead the algorithms. In this paper, we exploit the weakness of Machine Learning algorithms. We perform extensive experiments for the correctness of our results to exploit the weakness of machine learning algorithms. The methods are rigorously evaluated to validate our claim. In addition, this paper focuses on correctness of accuracy. This paper report three key outcomes of the experiments, namely, correctness of accuracies, significance of minimum accuracy, and correctness of machine learning algorithms.