Suresh Kothari

Bio: Suresh Kothari is an academic researcher from Iowa State University. The author has contributed to research in topics: Malware & Android (operating system). The author has an hindex of 9, co-authored 28 publications receiving 12787 citations.

Neural Networks for Pattern Recognition

Abstract: Publisher Summary This chapter provides an account of different neural network architectures for pattern recognition. A neural network consists of several simple processing elements called neurons. Each neuron is connected to some other neurons and possibly to the input nodes. Neural networks provide a simple computing paradigm to perform complex recognition tasks in real time. The chapter categorizes neural networks into three types: single-layer networks, multilayer feedforward networks, and feedback networks. It discusses the gradient descent and the relaxation method as the two underlying mathematical themes for deriving learning algorithms. A lot of research activity is centered on learning algorithms because of their fundamental importance in neural networks. The chapter discusses two important directions of research to improve learning algorithms: the dynamic node generation, which is used by the cascade correlation algorithm; and designing learning algorithms where the choice of parameters is not an issue. It closes with the discussion of performance and implementation issues.

Atlas: a new way to explore software, build analysis tools

Abstract: Atlas is a new software analysis platform from EnSoft Corp. Atlas decouples the domain-specific analysis goal from its underlying mechanism by splitting analysis into two distinct phases. In the first phase, polynomial-time static analyzers index the software AST, building a rich graph database. In the second phase, users can explore the graph directly or run custom analysis scripts written using a convenient API. These features make Atlas ideal for both interaction and automation. In this paper, we describe the motivation, design, and use of Atlas. We present validation case studies, including the verification of safe synchronization of the Linux kernel, and the detection of malware in Android applications. Our ICSE 2014 demo explores the comprehension and malware detection use cases. Video: http://youtu.be/cZOWlJ-IO0k

A Pattern-Based Framework for Software Anomaly Detection

Abstract: This paper presents a pattern-based framework for developing tool support to detect software anomalies. The use of a pattern-based approach is important because it provides the flexibility needed to address domain-specific needs, with respect to the types of problems the tools detect and the strategies used to inspect and adapt the code. Patterns can be used to detect a variety of problems, ranging from simple syntactic issues to difficult semantic problems requiring global analysis. Patterns can also be used to describe transformations of the software, used to rectify problems detected through software inspection, and to support interactive inspection and adaptation when full automation is impractical. This paper describes a part of the Knowledge Centric Software (KCS) framework that embodies the pattern-based approach and provides capabilities for addressing different languages and different application domains. While only the part of the framework relevant to code inspections is addressed in this paper, in future, we also expect to address UML analysis and design models. As an application of the research, we present an overview of an inspection tool being developed for high assurance software for avionics systems.

Statically-Informed Dynamic Analysis Tools to Detect Algorithmic Complexity Vulnerabilities

Abstract: Algorithmic Complexity (AC) vulnerabilities can be exploited to cause a denial of service attack. Specifically, an adversary can design an input to trigger excessive (space/time) resource consumption. It is not possible to build a fully automated tool to detect AC vulnerabilities. Since it is an open-ended problem, a human-in-loop exploration is required to find the program loops that could have AC vulnerabilities. Ascertaining whether an arbitrary loop has an AC vulnerability is itself difficult, which is equivalent to the halting problem. This paper is about a pragmatic engineering approach to detect AC vulnerabilities. It presents a statically-informed dynamic (SID) analysis and two tools that provide critical capabilities for detecting AC vulnerabilities. The first is a static analysis tool for exploring the software to find loops as the potential candidates for AC vulnerabilities. The second is a dynamic analysis tool that can try many different inputs to evaluate the selected loops for excessive resource consumption. The two tools are built and integrated together using the interactive software analysis, transformation, and visualization capabilities provided by the Atlas platform. The paper describes two use cases for the tools, one to detect AC vulnerabilities in Java bytecode and another for students in an undergraduate algorithm class to perform experiments to learn different aspects of algorithmic complexity Tool and Demo Video: https://ensoftcorp.github.io/SID.

Security toolbox for detecting novel and sophisticated android malware

Abstract: This paper presents a demo of our Security Toolbox to detect novel malware in Android apps. This Toolbox is developed through our recent research project funded by the DARPA Automated Program Analysis for Cybersecurity (APAC) project. The adversarial challenge ("Red") teams in the DARPA APAC program are tasked with designing sophisticated malware to test the bounds of malware detection technology being developed by the research and development ("Blue") teams. Our research group, a Blue team in the DARPA APAC program, proposed a "human-in-the-loop program analysis" approach to detect malware given the source or Java bytecode for an Android app. Our malware detection apparatus consists of two components: a general-purpose program analysis platform called Atlas, and a Security Toolbox built on the Atlas platform. This paper describes the major design goals, the Toolbox components to achieve the goals, and the workflow for auditing Android apps. The accompanying video illustrates features of the Toolbox through a live audit.Video: http://youtu.be/WhcoAX3HiNU

Deep Residual Learning for Image Recognition

Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Reinforcement Learning: An Introduction

Abstract: Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.

A Tutorial on Support Vector Machines for Pattern Recognition

Abstract: The tutorial starts with an overview of the concepts of VC dimension and structural risk minimization. We then describe linear Support Vector Machines (SVMs) for separable and non-separable data, working through a non-trivial example in detail. We describe a mechanical analogy, and discuss when SVM solutions are unique and when they are global. We describe how support vector training can be practically implemented, and discuss in detail the kernel mapping technique which is used to construct SVM solutions which are nonlinear in the data. We show how Support Vector machines can have very large (even infinite) VC dimension by computing the VC dimension for homogeneous polynomial and Gaussian radial basis function kernels. While very high VC dimension would normally bode ill for generalization performance, and while at present there exists no theory which shows that good generalization performance is guaranteed for SVMs, there are several arguments which support the observed high accuracy of SVMs, which we review. Results of some experiments which were inspired by these arguments are also presented. We give numerous examples and proofs of most of the key theorems. There is new material, and I hope that the reader will find that even old material is cast in a fresh light.

Machine learning

Abstract: Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

A tutorial on support vector regression

Abstract: In this tutorial we give an overview of the basic ideas underlying Support Vector (SV) machines for function estimation. Furthermore, we include a summary of currently used algorithms for training SV machines, covering both the quadratic (or convex) programming part and advanced methods for dealing with large datasets. Finally, we mention some modifications and extensions that have been applied to the standard SV algorithm, and discuss the aspect of regularization from a SV perspective.