Advances in machine learning (ML) in recent years have enabled a dizzying array of applications such as data analytics, autonomous systems, and security diagnostics. ML is now pervasive-new systems and models are being deployed in every domain imaginable, leading to rapid and widespread deployment of software based inference and decision making. There is growing recognition that ML exposes new vulnerabilities in software systems, yet the technical community's understanding of the nature and extent of these vulnerabilities remains limited. We systematize recent findings on ML security and privacy, focusing on attacks identified on these systems and defenses crafted to date. We articulate a comprehensive threat model for ML, and categorize attacks and defenses within an adversarial framework. Key insights resulting from works both in the ML and security communities are identified and the effectiveness of approaches are related to structural elements of ML algorithms and the data used to train them. We conclude by formally exploring the opposing relationship between model accuracy and resilience to adversarial manipulation. Through these explorations, we show that there are (possibly unavoidable) tensions between model complexity, accuracy, and resilience that must be calibrated for the environments in which they will be used.

Machines powered by artificial intelligence increasingly mediate our social, cultural, economic and political interactions. Understanding the behaviour of artificial intelligence systems is essential to our ability to control their actions, reap their benefits and minimize their harms. Here we argue that this necessitates a broad scientific research agenda to study machine behaviour that incorporates and expands upon the discipline of computer science and includes insights from across the sciences. We first outline a set of questions that are fundamental to this emerging field and then explore the technical, legal and institutional constraints on the study of machine behaviour.

No abstract

No abstract

Market price systems constitute a well-understood class of mechanisms that under certain conditions provide e ective decentralization of decision making with minimal communication overhead. In a market-oriented programming approach to distributed problem solving, we derive the activities and resource allocations for a set of computational agents by computing the competitive equilibrium of an arti cial economy. Walras provides basic constructs for de ning computational market structures, and protocols for deriving their corresponding price equilibria. In a particular realization of this approach for a form of multicommodity ow problem, we see that careful construction of the decision process according to economic principles can lead to e cient distributed resource allocation, and that the behavior of the system can be meaningfully analyzed in economic terms.