Can machine learning be secure?

Machine learning systems offer unparalled flexibility in dealing with evolving input in a variety of applications, such as intrusion detection systems and spam e-mail filtering. However, machine learning algorithms themselves can be a target of attack by a malicious adversary. This paper provides a framework for answering the question, "Can machine learning be secure?" Novel contributions of this paper include a taxonomy of different types of attacks on machine learning techniques and systems, a variety of defenses against those attacks, a discussion of ideas that are important to security for machine learning, an analytical model giving a lower bound on attacker's work function, and a list of open problems.

# Adversarial Robustness in Machine Learning # Computer Science # Security and Verification in Computing # Privacy-Preserving Technologies in Data

Marco Barreno, Blaine A. Nelson, Russell Sears, et al. (2006). "Can machine learning be secure?". ACM Asia Conference on Computer and Communications Security (ASIA CCS). https://doi.org/10.1145/1128817.1128824