View The Document

Accession Number:

AD1157105

Title:

Odyssey: A Systems Approach to Machine Learning Security

Author(s):

• Winder, Ransom
• ,
• Jubinski, Joseph
• Giannella, Chris
• Malachi, Jones

Author Organization(s):

• MITRE CORP ANNAPOLIS JUNCTION MD

Report Date:

2021-04-01

Abstract:

This paper provides a systems approach to addressing attacks, consequences, and mitigations for systems using Machine Learning (ML). It explains each of these over the lifecycle of an ML technology, providing clear explanations of what to worry about, when to worry about it, and how to mitigate it while presuming little incoming knowledge of ML specifics. Our discussion of ML vulnerabilities, attacks, and mitigations utilizes the taxonomy developed in NISTIR 8269.

Document Type:

Conference:

Journal:

Pages:

43

File Size:

1.88MB

Contracts:

Grants:

Descriptors:

• supervised machine learning
• neural networks
• artificial intelligence software
• data mining
• information science
• machine learning
• artificial intelligence
• cybersecurity
• unsupervised machine learning
• dimensionality reduction
• information processing
• information systems
• security
• systems approach
• computers
• computing devices
• reinforcement learning

Identifiers:

• AML(Adversarial Machine Learning)
• ML(machine learning)
• rl(Reinforcement Learning)
• ai(Artificial Intelligence)
• attack mitigation

SubjectCategory:

• Mathematical and Computer Sciences
• Behavioral and Social Sciences

Communities of Interest:

• Autonomy

Distribution Statement:

Approved For Public Release

View The Document