Law and Adversarial Machine Learning

Abstract

When machine learning systems fail because of adversarial manipulation, how should society expect the law to respond? Through scenarios grounded in adversarial ML literature, we explore how some aspects of computer crime, copyright, and tort law interface with perturbation, poisoning, model stealing and model inversion attacks to show how some attacks are more likely to result in liability than others. We end with a call for action to ML researchers to invest in transparent benchmarks of attacks and defenses; architect ML systems with forensics in mind and finally, think more about adversarial machine learning in the context of civil liberties. The paper is targeted towards ML researchers who have no legal background.

arXiv commentMinor edits. Corrected typos, Added references. 4 pages, submitted to NIPS 2018 Workshop on Security in Machine Learning

References in corpus (10)

• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Stealing Machine Learning Models via Prediction APIs
• Robust Physical-World Attacks on Deep Learning Models
• Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
• Motivating the Rules of the Game for Adversarial Example Research
• Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning
• Defense Against the Dark Arts: An overview of adversarial example security research and future research directions
• Security Risks in Deep Learning Implementations