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.

The Stackelberg Security Game (SSG) model has been immensely influential in security research since it was introduced roughly a decade ago. Furthermore, deployed SSG-based applications are one of most successful examples of game theory applications in the real world. We present a broad survey of recent technical advances in SSG and related literature, and then look to the future by highlighting the new potential applications and open research problems in SSG.

There is a significant body of empirical work on statistical de-anonymization attacks against databases containing micro-data about individuals, e.g., their preferences, movie ratings, or transaction data. Our goal is to analytically explain why such attacks work. Specifically, we analyze a variant of the Narayanan-Shmatikov algorithm that was used to effectively de-anonymize the Netflix database of movie ratings. We prove theorems characterizing mathematical properties of the database and the auxiliary information available to the adversary that enable two classes of privacy attacks. In the first attack, the adversary successfully identifies the individual about whom she possesses auxiliary information (an isolation attack). In the second attack, the adversary learns additional information about the individual, although she may not be able to uniquely identify him (an information amplification attack). We demonstrate the applicability of the analytical results by empirically verifying that the mathematical properties assumed of the database are actually true for a significant fraction of the records in the Netflix movie ratings database, which contains ratings from about 500,000 users.

We propose an approach to generate realistic and high-fidelity stock market data based on generative adversarial networks (GANs). Our Stock-GAN model employs a conditional Wasserstein GAN to capture history dependence of orders. The generator design includes specially crafted aspects including components that approximate the market's auction mechanism, augmenting the order history with order-book constructions to improve the generation task. We perform an ablation study to verify the usefulness of aspects of our network structure. We provide a mathematical characterization of distribution learned by the generator. We also propose statistics to measure the quality of generated orders. We test our approach with synthetic and actual market data, compare to many baseline generative models, and find the generated data to be close to real data.

Protocols for tasks such as authentication, electronic voting, and secure multiparty computation ensure desirable security properties if agents follow their prescribed programs. However, if some agents deviate from their prescribed programs and a security property is violated, it is important to hold agents accountable by determining which deviations actually caused the violation. Motivated by these applications, we initiate a formal study of program actions as actual causes. Specifically, we define in an interacting program model what it means for a set of program actions to be an actual cause of a violation. We present a sound technique for establishing program actions as actual causes. We demonstrate the value of this formalism in two ways. First, we prove that violations of a specific class of safety properties always have an actual cause. Thus, our definition applies to relevant security properties. Second, we provide a cause analysis of a representative protocol designed to address weaknesses in the current public key certification infrastructure.