Detecting Poisoning Attacks on Machine Learning in IoT Environments
Authors:
- Nathalie BaracaldoNBNathalie Baracaldo
- Bryant ChenBCBryant Chen
- Heiko LudwigHLHeiko Ludwig
- Amir SafaviASAmir Safavi
- Rui ZhangRZRui Zhang
- 1 July 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 57-64
Abstract
Machine Learning (ML) plays an increasing role in Internet of Things (IoT), both in the Cloud and at the Edge, using trained models for applications from factory automation to environmental sensing. However, using ML in IoT environments presents unique security challenges. In particular, adversaries can manipulate the training data by tampering with sensors' measurements. This type of attack, known as a poisoning attack has been shown to significantly decrease overall performance, cause targeted misclassification or bad behavior, and insert "backdoors" and "neural trojans". Taking advantage of recently developed tamper-free provenance frameworks, we present a methodology that uses contextual information about the origin and transformation of data points in the training set to identify poisonous data. Our approach works with or without a trusted test data set. Using the proposed approach poisoning attacks can be effectively detected and mitigated in IoT environments with reliable provenance information.Keywords
This publication has 9 references indexed in Scilit:
- Neural Trojans2017
- Securing Data Provenance in Internet of Things (IoT) Systems2017
- Secure Data Provenance for the Internet of Things2017
- On the Security of Machine Learning in Malware C&C DetectionACM Computing Surveys, 2016
- Systematic Poisoning Attacks on and Defenses for Machine Learning in HealthcareIEEE Journal of Biomedical and Health Informatics, 2014
- Security Evaluation of Pattern Classifiers under AttackIEEE Transactions on Knowledge and Data Engineering, 2014
- Adversarial machine learning2011
- The security of machine learningMachine Learning, 2010
- Misleading Learners: Co-opting Your Spam Filter2009