arXiv subjects

Margo Seltzer

Publications and source records attributed to Margo Seltzer.

At least 37 records · Page 2Linked to original sources

arXiv2023

OSmosis: No more Déjà vu in OS isolation

Operating systems provide an abstraction layer between the hardware and higher-level software. Many abstractions, such as threads, processes, containers, and virtual machines, are mechanisms to provide isolation. New application scenarios frequently introduce new isolation mechanisms. Implementing each isolation mechanism as an independent abstraction makes it difficult to reason about the state and resources shared among different tasks, leading to security vulnerabilities and performance interference. We present OSmosis, an isolation model that expresses the precise level of resource sharing, a framework in which to implement isolation mechanisms based on the model, and an implementation of the framework on seL4. The OSmosis model lets the user determine the degree of isolation guarantee that they need from the system. This determination empowers developers to make informed decisions about isolation and performance trade-offs, and the framework enables them to create mechanisms with the desired degree of isolation.

cs.CR↗

arXiv2023

Optimal Sparse Regression Trees

Regression trees are one of the oldest forms of AI models, and their predictions can be made without a calculator, which makes them broadly useful, particularly for high-stakes applications. Within the large literature on regression trees, there has been little effort towards full provable optimization, mainly due to the computational hardness of the problem. This work proposes a dynamic-programming-with-bounds approach to the construction of provably-optimal sparse regression trees. We leverage a novel lower bound based on an optimal solution to the k-Means clustering algorithm in 1-dimension over the set of labels. We are often able to find optimal sparse trees in seconds, even for challenging datasets that involve large numbers of samples and highly-correlated features.

cs.LG↗

arXiv2022

Generalized and Scalable Optimal Sparse Decision Trees

Decision tree optimization is notoriously difficult from a computational perspective but essential for the field of interpretable machine learning. Despite efforts over the past 40 years, only recently have optimization breakthroughs been made that have allowed practical algorithms to find optimal decision trees. These new techniques have the potential to trigger a paradigm shift where it is possible to construct sparse decision trees to efficiently optimize a variety of objective functions without relying on greedy splitting and pruning heuristics that often lead to suboptimal solutions. The contribution in this work is to provide a general framework for decision tree optimization that addresses the two significant open problems in the area: treatment of imbalanced data and fully optimizing over continuous variables. We present techniques that produce optimal decision trees over a variety of objectives including F-score, AUC, and partial area under the ROC convex hull. We also introduce a scalable algorithm that produces provably optimal results in the presence of continuous variables and speeds up decision tree construction by several orders of magnitude relative to the state-of-the art.

cs.LG↗

arXiv2022

Anomaly Detection in Multiplex Dynamic Networks: from Blockchain Security to Brain Disease Prediction

The problem of identifying anomalies in dynamic networks is a fundamental task with a wide range of applications. However, it raises critical challenges due to the complex nature of anomalies, lack of ground truth knowledge, and complex and dynamic interactions in the network. Most existing approaches usually study networks with a single type of connection between vertices, while in many applications interactions between objects vary, yielding multiplex networks. We propose ANOMULY, a general, unsupervised edge anomaly detection framework for multiplex dynamic networks. In each relation type, ANOMULY sees node embeddings at different GNN layers as hierarchical node states and employs a GRU cell to capture temporal properties of the network and update node embeddings over time. We then add an attention mechanism that incorporates information across different types of relations. Our case study on brain networks shows how this approach could be employed as a new tool to understand abnormal brain activity that might reveal a brain disease or disorder. Extensive experiments on nine real-world datasets demonstrate that ANOMULY achieves state-of-the-art performance.

cs.LG↗

arXiv2022

Fast Sparse Classification for Generalized Linear and Additive Models

We present fast classification techniques for sparse generalized linear and additive models. These techniques can handle thousands of features and thousands of observations in minutes, even in the presence of many highly correlated features. For fast sparse logistic regression, our computational speed-up over other best-subset search techniques owes to linear and quadratic surrogate cuts for the logistic loss that allow us to efficiently screen features for elimination, as well as use of a priority queue that favors a more uniform exploration of features. As an alternative to the logistic loss, we propose the exponential loss, which permits an analytical solution to the line search at each iteration. Our algorithms are generally 2 to 5 times faster than previous approaches. They produce interpretable models that have accuracy comparable to black box models on challenging datasets.

cs.LG↗

arXiv2022

Exploring the Whole Rashomon Set of Sparse Decision Trees

In any given machine learning problem, there may be many models that could explain the data almost equally well. However, most learning algorithms return only one of these models, leaving practitioners with no practical way to explore alternative models that might have desirable properties beyond what could be expressed within a loss function. The Rashomon set is the set of these all almost-optimal models. Rashomon sets can be extremely complicated, particularly for highly nonlinear function classes that allow complex interaction terms, such as decision trees. We provide the first technique for completely enumerating the Rashomon set for sparse decision trees; in fact, our work provides the first complete enumeration of any Rashomon set for a non-trivial problem with a highly nonlinear discrete function class. This allows the user an unprecedented level of control over model choice among all models that are approximately equally good. We represent the Rashomon set in a specialized data structure that supports efficient querying and sampling. We show three applications of the Rashomon set: 1) it can be used to study variable importance for the set of almost-optimal trees (as opposed to a single tree), 2) the Rashomon set for accuracy enables enumeration of the Rashomon sets for balanced accuracy and F1-score, and 3) the Rashomon set for a full dataset can be used to produce Rashomon sets constructed with only subsets of the data set. Thus, we are able to examine Rashomon sets across problems with a new lens, enabling users to choose models rather than be at the mercy of an algorithm that produces only a single model.

cs.LG↗

arXiv2022

Fast Optimization of Weighted Sparse Decision Trees for use in Optimal Treatment Regimes and Optimal Policy Design

Sparse decision trees are one of the most common forms of interpretable models. While recent advances have produced algorithms that fully optimize sparse decision trees for prediction, that work does not address policy design, because the algorithms cannot handle weighted data samples. Specifically, they rely on the discreteness of the loss function, which means that real-valued weights cannot be directly used. For example, none of the existing techniques produce policies that incorporate inverse propensity weighting on individual data points. We present three algorithms for efficient sparse weighted decision tree optimization. The first approach directly optimizes the weighted loss function; however, it tends to be computationally inefficient for large datasets. Our second approach, which scales more efficiently, transforms weights to integer values and uses data duplication to transform the weighted decision tree optimization problem into an unweighted (but larger) counterpart. Our third algorithm, which scales to much larger datasets, uses a randomized procedure that samples each data point with a probability proportional to its weight. We present theoretical bounds on the error of the two fast methods and show experimentally that these methods can be two orders of magnitude faster than the direct optimization of the weighted loss, without losing significant accuracy.

cs.LG↗

arXiv2022

FasterRisk: Fast and Accurate Interpretable Risk Scores

Over the last century, risk scores have been the most popular form of predictive model used in healthcare and criminal justice. Risk scores are sparse linear models with integer coefficients; often these models can be memorized or placed on an index card. Typically, risk scores have been created either without data or by rounding logistic regression coefficients, but these methods do not reliably produce high-quality risk scores. Recent work used mathematical programming, which is computationally slow. We introduce an approach for efficiently producing a collection of high-quality risk scores learned from data. Specifically, our approach produces a pool of almost-optimal sparse continuous solutions, each with a different support set, using a beam-search algorithm. Each of these continuous solutions is transformed into a separate risk score through a "star ray" search, where a range of multipliers are considered before rounding the coefficients sequentially to maintain low logistic loss. Our algorithm returns all of these high-quality risk scores for the user to consider. This method completes within minutes and can be valuable in a broad variety of applications.

cs.LG↗

arXiv2022

TimberTrek: Exploring and Curating Sparse Decision Trees with Interactive Visualization

Given thousands of equally accurate machine learning (ML) models, how can users choose among them? A recent ML technique enables domain experts and data scientists to generate a complete Rashomon set for sparse decision trees--a huge set of almost-optimal interpretable ML models. To help ML practitioners identify models with desirable properties from this Rashomon set, we develop TimberTrek, the first interactive visualization system that summarizes thousands of sparse decision trees at scale. Two usage scenarios highlight how TimberTrek can empower users to easily explore, compare, and curate models that align with their domain knowledge and values. Our open-source tool runs directly in users' computational notebooks and web browsers, lowering the barrier to creating more responsible ML models. TimberTrek is available at the following public demo link: https://poloclub.github.io/timbertrek.

cs.HC↗

arXiv2022

Fast Sparse Decision Tree Optimization via Reference Ensembles

Sparse decision tree optimization has been one of the most fundamental problems in AI since its inception and is a challenge at the core of interpretable machine learning. Sparse decision tree optimization is computationally hard, and despite steady effort since the 1960's, breakthroughs have only been made on the problem within the past few years, primarily on the problem of finding optimal sparse decision trees. However, current state-of-the-art algorithms often require impractical amounts of computation time and memory to find optimal or near-optimal trees for some real-world datasets, particularly those having several continuous-valued features. Given that the search spaces of these decision tree optimization problems are massive, can we practically hope to find a sparse decision tree that competes in accuracy with a black box machine learning model? We address this problem via smart guessing strategies that can be applied to any optimal branch-and-bound-based decision tree algorithm. We show that by using these guesses, we can reduce the run time by multiple orders of magnitude, while providing bounds on how far the resulting trees can deviate from the black box's accuracy and expressive power. Our approach enables guesses about how to bin continuous features, the size of the tree, and lower bounds on the error for the optimal decision tree. Our experiments show that in many cases we can rapidly construct sparse decision trees that match the accuracy of black box models. To summarize: when you are having trouble optimizing, just guess.

cs.LG↗

arXiv2022

Gridiron: A Technique for Augmenting Cloud Workloads with Network Bandwidth Requirements

Cloud applications use more than just server resources, they also require networking resources. We propose a new technique to model network bandwidth demand of networked cloud applications. Our technique, Gridiron, augments VM workload traces from Azure cloud with network bandwidth requirements. The key to the Gridiron technique is to derive inter-VM network bandwidth requirements using Amdahl's second law. As a case study, we use Gridiron to generate realistic traces with network bandwidth demands for a distributed machine learning training application. Workloads generated with Gridiron allow datacenter operators to estimate the network bandwidth demands of cloud applications and enable more realistic cloud resource scheduler evaluation.

cs.DC↗

arXiv2021

SIGL: Securing Software Installations Through Deep Graph Learning

Many users implicitly assume that software can only be exploited after it is installed. However, recent supply-chain attacks demonstrate that application integrity must be ensured during installation itself. We introduce SIGL, a new tool for detecting malicious behavior during software installation. SIGL collects traces of system call activity, building a data provenance graph that it analyzes using a novel autoencoder architecture with a graph long short-term memory network (graph LSTM) for the encoder and a standard multilayer perceptron for the decoder. SIGL flags suspicious installations as well as the specific installation-time processes that are likely to be malicious. Using a test corpus of 625 malicious installers containing real-world malware, we demonstrate that SIGL has a detection accuracy of 96%, outperforming similar systems from industry and academia by up to 87% in precision and recall and 45% in accuracy. We also demonstrate that SIGL can pinpoint the processes most likely to have triggered malicious behavior, works on different audit platforms and operating systems, and is robust to training data contamination and adversarial attack. It can be used with application-specific models, even in the presence of new software versions, as well as application-agnostic meta-models that encompass a wide range of applications and installers.

cs.CR↗

arXiv2021

ReLUSyn: Synthesizing Stealthy Attacks for Deep Neural Network Based Cyber-Physical Systems

Cyber Physical Systems (cps) are deployed in many mission-critical settings, such as medical devices, autonomous vehicular systems and aircraft control management systems. As more and more CPS adopt Deep Neural Networks (Deep Neural Network (dnns), these systems can be vulnerable to attacks. . Prior work has demonstrated the susceptibility of CPS to False Data Injection Attacks (False Data Injection Attacks (fdias), which can cause significant damage. We identify a new category of attacks on these systems. In this paper, we demonstrate that DNN based CPS are also subject to these attacks. These attacks, which we call Ripple False Data Injection Attacks (rfdia), use minimal input perturbations to stealthily change the dnn output. The input perturbations propagate as ripples through multiple dnn layers to affect the output in a targeted manner. We develop an automated technique to synthesize rfdias against DNN-based CPS. Our technique models the attack as an optimization problem using Mixed Integer Linear Programming (Mixed Integer Linear Program (milp)). We define an abstraction for dnnbased cps that allows us to automatically: 1) identify the critical inputs, and 2) find the smallest perturbations that produce output changes. We demonstrate our technique on three practical cps with two mission-critical applications: an (Artifical Pancreas System (aps)) and two aircraft control management systems (Horizontal Collision Avoidance System (hcas) and Collision Avoidance System-Xu (acas-xu)).

eess.SY↗

arXiv2020

Parking Packet Payload with P4

Network Function (NF) deployments suffer from poor link goodput, because popular NFs such as firewalls process only packet headers while receiving and transmitting complete packets. As a result, unnecessary packet payloads needlessly consume link bandwidth. We introduce PayloadPark, which improves goodput by temporarily parking packet payloads in the stateful memory of dataplane programmable switches. PayloadPark forwards only packet headers to NF servers, thereby saving bandwidth between the switch and the NF server. PayloadPark is a transparent in-network optimization that complements existing approaches for optimizing NF performance on end-hosts. We prototyped PayloadPark on a Barefoot Tofino ASIC using the P4 language. Our prototype, when deployed on a top-of-rack switch, can service up to 8 NF servers using less than 40% of the on-chip memory resources. The prototype improves goodput by 10- 36% for Firewall and NAT NFs and by 10-26% for a Firewall -> NAT NF chain without harming latency. The prototype also reduces PCIe bus load by 2-58% on the NF server thanks to the reduced data transmission between the switch and the NF server. With workloads that have datacenter network traffic characteristics, PayloadPark provides a 13% goodput gain with the Firewall -> NAT -> LB NF chain without latency penalty. In the same setup, we can further increase the goodput gain to 28% by using packet recirculation.

cs.NI↗

arXiv2020

The EuroSys 2020 Online Conference: Experience and lessons learned

The 15th European Conference on Computer Systems (EuroSys'20) was organized as a virtual (online) conference on April 27-30, 2020. The main EuroSys'20 track took place April 28-30, 2020, preceded by five workshops (EdgeSys'20, EuroDW'20, EuroSec'20, PaPoC'20, SPMA'20) on April 27, 2020. The decision to hold a virtual (online) conference was taken in early April 2020, after consultations with the EuroSys community and internal discussions about potential options, eventually allowing about three weeks for the organization. This paper describes the choices we made to organize EuroSys'20 as a virtual (online) conference, the challenges we addressed, and the lessons learned.

cs.CY↗

arXiv2020

Xanthus: Push-button Orchestration of Host Provenance Data Collection

Host-based anomaly detectors generate alarms by inspecting audit logs for suspicious behavior. Unfortunately, evaluating these anomaly detectors is hard. There are few high-quality, publicly-available audit logs, and there are no pre-existing frameworks that enable push-button creation of realistic system traces. To make trace generation easier, we created Xanthus, an automated tool that orchestrates virtual machines to generate realistic audit logs. Using Xanthus' simple management interface, administrators select a base VM image, configure a particular tracing framework to use within that VM, and define post-launch scripts that collect and save trace data. Once data collection is finished, Xanthus creates a self-describing archive, which contains the VM, its configuration parameters, and the collected trace data. We demonstrate that Xanthus hides many of the tedious (yet subtle) orchestration tasks that humans often get wrong; Xanthus avoids mistakes that lead to non-replicable experiments.

cs.CR↗

arXiv2020

UNICORN: Runtime Provenance-Based Detector for Advanced Persistent Threats

Advanced Persistent Threats (APTs) are difficult to detect due to their "low-and-slow" attack patterns and frequent use of zero-day exploits. We present UNICORN, an anomaly-based APT detector that effectively leverages data provenance analysis. From modeling to detection, UNICORN tailors its design specifically for the unique characteristics of APTs. Through extensive yet time-efficient graph analysis, UNICORN explores provenance graphs that provide rich contextual and historical information to identify stealthy anomalous activities without pre-defined attack signatures. Using a graph sketching technique, it summarizes long-running system execution with space efficiency to combat slow-acting attacks that take place over a long time span. UNICORN further improves its detection capability using a novel modeling approach to understand long-term behavior as the system evolves. Our evaluation shows that UNICORN outperforms an existing state-of-the-art APT detection system and detects real-life APT scenarios with high accuracy.

cs.CR↗

arXiv2019

ProvMark: A Provenance Expressiveness Benchmarking System

System level provenance is of widespread interest for applications such as security enforcement and information protection. However, testing the correctness or completeness of provenance capture tools is challenging and currently done manually. In some cases there is not even a clear consensus about what behavior is correct. We present an automated tool, ProvMark, that uses an existing provenance system as a black box and reliably identifies the provenance graph structure recorded for a given activity, by a reduction to subgraph isomorphism problems handled by an external solver. ProvMark is a beginning step in the much needed area of testing and comparing the expressiveness of provenance systems. We demonstrate ProvMark's usefuless in comparing three capture systems with different architectures and distinct design philosophies.

cs.CR↗