Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks

by   Kendra Albert, et al.

Attacks from adversarial machine learning (ML) have the potential to be used "for good": they can be used to run counter to the existing power structures within ML, creating breathing space for those who would otherwise be the targets of surveillance and control. But most research on adversarial ML has not engaged in developing tools for resistance against ML systems. Why? In this paper, we review the broader impact statements that adversarial ML researchers wrote as part of their NeurIPS 2020 papers and assess the assumptions that authors have about the goals of their work. We also collect information about how authors view their work's impact more generally. We find that most adversarial ML researchers at NeurIPS hold two fundamental assumptions that will make it difficult for them to consider socially beneficial uses of attacks: (1) it is desirable to make systems robust, independent of context, and (2) attackers of systems are normatively bad and defenders of systems are normatively good. That is, despite their expressed and supposed neutrality, most adversarial ML researchers believe that the goal of their work is to secure systems, making it difficult to conceptualize and build tools for disrupting the status quo.


"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice

Recent years have seen a proliferation of research on adversarial machin...

Law and Adversarial Machine Learning

When machine learning systems fail because of adversarial manipulation, ...

Adversarial Attacks on Machine Learning in Embedded and IoT Platforms

Machine learning (ML) algorithms are increasingly being integrated into ...

Legal Risks of Adversarial Machine Learning Research

Adversarial Machine Learning is booming with ML researchers increasingly...

Adaversarial Issue of Machine Learning Approaches Applied in Smart Grid: A Survey

The machine learning (ML) sees an increasing prevalence of being used in...

The Values Encoded in Machine Learning Research

Machine learning (ML) currently exerts an outsized influence on the worl...

AI Ethics Statements – Analysis and lessons learnt from NeurIPS Broader Impact Statements

Ethics statements have been proposed as a mechanism to increase transpar...

Please sign up or login with your details

Forgot password? Click here to reset