In recent years, trusted execution environments (TEEs) such as Intel Software Guard Extensions (SGX) have gained a lot of attention in the database community. This is because TEEs provide an interesting platform for building trusted databases in the cloud. However, until recently SGX was only available on low-end single socket servers built on the Intel Xeon E3 processor generation and came with many restrictions for building DBMSs. With the availability of the new Ice Lake processors, Intel provides a new implementation of the SGX technology that supports high-end multi-socket servers. With this new implementation, which we refer to as SGXv2 in this paper, Intel promises to address several limitations of SGX enclaves. This raises the question whether previous efforts to overcome the limitations of SGX for DBMSs are still applicable and if the new generation of SGX can truly deliver on the promise to secure data without compromising on performance. To answer this question, in this paper we conduct a first systematic performance study of Intel SGXv2 and compare it to the previous generation of SGX.

Federated learning aims to protect the privacy of data owners in a collaborative machine learning setup since training data does not need to be revealed to any other participant involved in the training process. This is achieved by only requiring participants to share locally computed model updates (i.e., gradients), instead of the training data, with a centralized parameter server. However, recent papers have shown that privacy attacks exist which allow this server to reconstruct the training data of individual data owners only from the received gradients. To mitigate this attack, in this paper, we propose a new federated learning framework that decentralizes the parameter server. As part of this contribution, we investigate the configuration space of such a decentralized federated learning framework. Moreover, we propose three promising privacy-preserving techniques, namely model sharding, asynchronous updates and polling intervals for stale parameters. In our evaluation, we observe on different data sets that these techniques can effectively thwart the gradient-based reconstruction attacks on deep learning models, both from the client side and the server side, by reducing the attack results close to random noise.

End-to-end encrypted relational database management systems (EDBs) are the “holy grail” of database security and have been studied by the research community for the last 20 years. During this time, several systems have been proposed with a variety of limitations that include weak security, poor performance and restricted query expressiveness. We contend that this state of affairs is due, in part, to a lack of cohesion between the techniques and methodologies of the database and cryptography communities. We believe that the only way to make significant progress on this important problem is to properly leverage techniques and ideas from the two communities. Towards this end, we identify five key design principles for end-to-end encrypted relational databases. These principles include security, performance and expressiveness considerations. We describe a system called KafeDB ; the first encrypted relational database system that meets these principles. KafeDB is based on a new database encryption scheme called OPX that supports a nontrivial subset of SQL queries. Our prototype, built on top of PostgreSQL , shows the feasibility of our approach. TPC-H shows our prototype is about one to three order of magnitude slower than optimized plain-text PostgreSQL and requires about one order of magnitude more storage while offering end-to-end security.

Recently, Kamara and Moataz described the first encrypted relational database solution with support for a non-trivial fraction of SQL that does not make use of property-preserving encryption (Asiacrypt, 2018). More precisely, their construction, called SPX, handles the set of conjunctive SQL queries. While SPX was shown to be optimal for the subset of uncorrelated conjunctive SQL queries, it did not handle correlated queries optimally. Furthermore, it only handles queries in heuristic normal form. In this work, we address these limitations by proposing an extension of SPX that handles all conjunctive SQL queries optimally no matter what form they are in. ∗seny@brown.edu †tarik@aroki.com ‡sbz@cs.brown.edu §zheguang.zhao@brown.edu

The goal of a visualization system is to facilitate dataset-driven insight discovery. But what if the insights are spurious? Features or patterns in visualizations can be perceived as relevant insights, even though they may arise from noise. We often compare visualizations to a mental image of what we are interested in: a particular trend, distribution or an unusual pattern. As more visualizations are examined and more comparisons are made, the probability of discovering spurious insights increases. This problem is well-known in Statistics as the multiple comparisons problem (MCP) but overlooked in visual analysis. We present a way to evaluate MCP in visualization tools by measuring the accuracy of user reported insights on synthetic datasets with known ground truth labels. In our experiment, over 60% of user insights were false. We show how a confirmatory analysis approach that accounts for all visual comparisons, insights and non-insights, can achieve similar results as one that requires a validation dataset.

Recent tools for interactive data exploration significantly increase the chance that users make false discoveries. They allow users to (visually) examine many hypotheses and make inference with simple interactions, and thus incur the issue commonly known in statistics as the " multiple hypothesis testing error ." In this work, we propose a solution to integrate the control of multiple hypothesis testing into interactive data exploration systems. A key insight is that existing methods for controlling the false discovery rate (such as FDR) are not directly applicable to interactive data exploration. We therefore discuss a set of new control procedures that are better suited for this task and integrate them in our system, QUDE. Via extensive experiments on both real-world and synthetic data sets we demonstrate how QUDE can help experts and novice users alike to efficiently control false discoveries.

Have you ever been in a sauna? If yes, according to our recent survey conducted on Amazon Mechanical Turk, people who go to saunas are more likely to know that Mike Stonebraker is not a character in “The Simpsons”. While this result clearly makes no sense, recently proposed tools to automatically suggest visualizations, correlations, or perform visual data exploration, significantly increase the chance that a user makes a false discovery like this one. In this paper, we first show how current tools mislead users to consider random fluc-tuations as significant discoveries. We then describe our vision and early results for QUDE, a new system for automatically controlling the various risk factors during the data exploration process.

Apache Spark is a popular framework for data analytics with attractive features such as fault tolerance and interoperability with the Hadoop ecosystem. Unfortunately, many analytics operations in Spark are an order of magnitude or more slower compared to native implementations written with high performance computing tools such as MPI. There is a need to bridge the performance gap while retaining the benefits of the Spark ecosystem such as availability, productivity, and fault tolerance. In this paper, we propose a system for integrating MPI with Spark and analyze the costs and benefits of doing so for four distributed graph and machine learning applications. We show that offloading computation to an MPI environment from within Spark provides 3.1−17.7× speedups on the four sparse applications, including all of the overheads. This opens up an avenue to reuse existing MPI libraries in Spark with little effort.

Exploring data via visualization has become a popular way to understand complex data. Features or patterns in visualization can be perceived as relevant insights by users, even though they may actually arise from random noise. Moreover, interactive data exploration and visualization recommendation tools can examine a large number of observations, and therefore result in further increasing chance of spurious insights. Thus without proper statistical control, the risk of false discovery renders visual data exploration unsafe and makes users susceptible to questionable inference.To address these problems, we present QUDE, a visual data exploration system that interacts with users to formulate hypotheses based on visualizations and provides interactive control of false discoveries.

Memory-based data center applications require increasingly large memory capacities, but face the challenges posed by the inherent difficulties in scaling DRAM and also the cost of DRAM. Future systems are attempting to address these demands with heterogeneous memory architectures coupling DRAM with high capacity, low cost, but also lower performance, non-volatile memories (NVM) such as PCM and RRAM. A key usage model intended for NVM is as cheaper high capacity volatile memory. Data center operators are bound to ask whether this model for the usage of NVM to replace the majority of DRAM memory leads to a large slowdown in their applications? It is crucial to answer this question because a large performance impact will be an impediment to the adoption of such systems. This paper presents a thorough study of representative applications -- including a key-value store (MemC3), an in-memory database (VoltDB), and a graph analytics framework (GraphMat) -- on a platform that is capable of emulating a mix of memory technologies. Our conclusions are that it is indeed possible to use a mix of a small amount of fast DRAM and large amounts of slower NVM without a proportional impact to an application's performance. The caveat is that this result can only be achieved through careful placement of data structures. The contribution of this paper is the design and implementation of a set of libraries and automatic tools that enables programmers to achieve optimal data placement with minimal effort on their part. With such guided placement and with DRAM constituting only 6% of the total memory footprint for GraphMat and 25% for VoltDB and MemC3 (remaining memory is NVM with 4x higher latency and 8x lower bandwidth than DRAM), we show that our target applications demonstrate only a 13% to 40% slowdown. Without guided placement, these applications see, in the worst case, 1.5x to 5.9x slowdown on the same configuration. Based on a realistic assumption that NVM will be 5x cheaper (per bit) than DRAM, this hybrid solution also results in 2x to 2.8x better performance/$ than a DRAM-only system.

Existing benchmarks for analytical database systems such as TPC-DS and TPC-H are designed for static reporting scenarios. The main metric of these benchmarks is the performance of running different SQL queries over a predefined database. In this paper, we argue that such benchmarks are not suitable for evaluating modern interactive data exploration (IDE) systems, which allow data scientists of varying skill levels to manipulate, analyze, and explore large data sets, as well as to build models and apply machine learning at interactive speeds. While query performance is still important for data exploration, we believe that a much better metric would reflect the number and complexity of insights users gain in a given amount of time. This paper discusses challenges of creating such a metric and presents ideas towards a new benchmark that simulates typical user behavior and allows IDE systems to be compared in a reproducible way.

Visualizations are arguably the most important tool to explore, understand and convey facts about data. As part of interactive data exploration, visualizations might be used to quickly skim through the data and look for patterns. Unfortunately, database systems are not designed to efficiently support these workloads. As a result, visualizations often take very long to produce, creating a significant barrier to interactive data analysis. In this paper, we focus on the interactive computation of histograms for data exploration. To address this issue, we present a novel multi-dimensional index structure called VisTree . As a key contribution, this paper presents several techniques to better align the design of multi-dimensional indexes with the needs of visualization tools for data exploration. Our experiments show that the VisTree achieves a speed increase of up to three orders of magnitude compared to traditional multi-dimensional indexes and enables an interactive speed of below 500ms even on large data sets.

Visualizations are arguably the most important tool to explore, understand and convey facts about data. As part of interactive data exploration, visualizations might be used to quickly skim through the data and look for patterns. Unfortunately, database systems are not designed to efficiently support these workloads. As a result, visualizations often take very long to produce, creating a significant barrier to interactive data analysis.

Recently, a new class of systems for shared and collaborative data management has gained more and more traction. Different from classical DBMSs, systems for shared data need to provide additional guarantees to ensure the integrity of data and transaction execution. In this paper, we propose to extend the ACID properties used by classical DBMSs with a new Verifiability component to enable users to specify the required guarantees of verifiability in a declarative manner.