Law and Adversarial Machine Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningSimilar Papers 제목 키워드 기반
An Optimal Control View of Adversarial Machine Learning
I describe an optimal control view of adversarial machine learning, where the dynamical system is the machine learner, the input are adversarial actions, and the control costs are defined by the adversary's goals to do h…
BIG-bench Machine LearningData Poisoningreinforcement-learningReinforcement Learning+1The Threat of Adversarial Attacks on Machine Learning in Network Security -- A Survey
Machine learning models have made many decision support systems to be faster, more accurate, and more efficient. However, applications of machine learning in network security face a more disproportionate threat of active…
BIG-bench Machine LearningClassificationGeneral ClassificationIntrusion Detection+1Quantum Adversarial Machine Learning: From Classical Adaptations to Quantum-Native Methods
Machine learning has revolutionized numerous industrial domains. Despite recent advances, machine learning models remain vulnerable to adversarial threats. Adversarial machine learning is a field that studies these vulne…
Quantum Machine LearningAdversarial Machine Learning Attacks on Condition-Based Maintenance Capabilities
Condition-based maintenance (CBM) strategies exploit machine learning models to assess the health status of systems based on the collected data from the physical environment, while machine learning models are vulnerable …
BIG-bench Machine LearningDefending Against Adversarial Machine Learning
An Adversarial System to attack and an Authorship Attribution System (AAS) to defend itself against the attacks are analyzed. Defending a system against attacks from an adversarial machine learner can be done by randomly…
Authorship AttributionBIG-bench Machine Learning