Understanding users' perceptions of suspected computer-security problems can help us tailor technology to better protect users. To this end, we conducted a field study of users' perceptions using 189,272 problem descriptions sent to the customer-support desk of a large anti-virus vendor from 2015 to 2018. Using qualitative methods, we analyzed 650 problem descriptions to study the security issues users faced and the symptoms that led users to their own diagnoses. Subsequently, we investigated to what extent and for what types of issues user diagnoses matched those of experts. We found, for example, that users and experts were likely to agree for most issues, but not for attacks (e.g., malware infections), for which they agreed only in 44% of the cases. Our findings inform several user-security improvements, including how to automate interactions with users to resolve issues and to better communicate issues to users.

In this work, we define a collaborative and privacy-preserving machine teaching paradigm with multiple distributed teachers. We focus on consensus super teaching. It aims at organizing distributed teachers to jointly select a compact while informative training subset from data hosted by the teachers to make a learner learn better. The challenges arise from three perspectives. First, the state-of-the-art pool-based super teaching method applies mixed-integer non-linear programming (MINLP) which does not scale well to very large data sets. Second, it is desirable to restrict data access of the teachers to only their own data during the collaboration stage to mitigate privacy leaks. Finally, the teaching collaboration should be communication-efficient since large communication overheads can cause synchronization delays between teachers. To address these challenges, we formulate the collaborative teaching as a consensus and privacy-preserving optimization process to minimize teaching risk. We theoretically demonstrate the necessity of collaboration between teachers for improving the learner's learning. Furthermore, we show that the proposed method enjoys a similar property as the Oracle property of adaptive Lasso. Empirical study illustrates that our teaching method can deliver significantly more accurate teaching results with high speed, while the non-collaborative MINLP-based super teaching becomes prohibitively expensive to compute.

Finding patterns in graphs has become a vital challenge in many domains from biological systems, network security, to finance (e.g., finding money laundering rings of bankers and business owners). While there is significant interest in graph databases and querying techniques, less research has focused on helping analysts make sense of underlying patterns within a group of subgraph results. Visualizing graph query results is challenging, requiring effective summarization of a large number of subgraphs, each having potentially shared node-values, rich node features, and flexible structure across queries. We present VIGOR, a novel interactive visual analytics system, for exploring and making sense of query results. VIGOR uses multiple coordinated views, leveraging different data representations and organizations to streamline analysts sensemaking process. VIGOR contributes: (1) an exemplar-based interaction technique, where an analyst starts with a specific result and relaxes constraints to find other similar results or starts with only the structure (i.e., without node value constraints), and adds constraints to narrow in on specific results; and (2) a novel feature-aware subgraph result summarization. Through a collaboration with Symantec, we demonstrate how VIGOR helps tackle real-world problems through the discovery of security blindspots in a cybersecurity dataset with over 11,000 incidents. We also evaluate VIGOR with a within-subjects study, demonstrating VIGOR's ease of use over a leading graph database management system, and its ability to help analysts understand their results at higher speed and make fewer errors.

Cybersecurity analysts are often presented suspicious machine activity that does not conclusively indicate compromise, resulting in undetected incidents or costly investigations into the most appropriate remediation actions. There are many reasons for this: deficiencies in the number and quality of security products that are deployed, poor configuration of those security products, and incomplete reporting of product-security telemetry. Managed Security Service Providers (MSSP's), which are tasked with detecting security incidents on behalf of multiple customers, are confronted with these data quality issues, but also possess a wealth of cross-product security data that enables innovative solutions. We use MSSP data to develop Virtual Product, which addresses the aforementioned data challenges by predicting what security events would have been triggered by a security product if it had been present. This benefits the analysts by providing more context into existing security incidents (albeit probabilistic) and by making questionable security incidents more conclusive. We achieve up to 99% AUC in predicting the incidents that some products would have detected had they been present.

We study a dataset of billions of program binary files that appeared on 100 million computers over the course of 12 months, discovering that 94% of these files were present on a single machine. Though malware polymorphism is one cause for the large number of singleton files, additional factors also contribute to polymorphism, given that the ratio of benign to malicious singleton files is 80:1. The huge number of benign singletons makes it challenging to reliably identify the minority of malicious singletons. We present a large-scale study of the properties, characteristics, and distribution of benign and malicious singleton files. We leverage the insights from this study to build a classifier based purely on static features to identify 92% of the remaining malicious singletons at a 1.4% percent false positive rate, despite heavy use of obfuscation and packing techniques by most malicious singleton files that we make no attempt to de-obfuscate. Finally, we demonstrate robustness of our classifier to important classes of automated evasion attacks.

Understanding how to group a set of binary files into the piece of software they belong to is highly desirable for software profiling, malware detection, or enterprise audits, among many other applications. Unfortunately, it is also extremely challenging: there is absolutely no uniformity in the ways different applications rely on different files, in how binaries are signed, or in the versioning schemes used across different pieces of software. In this paper, we show that, by combining information gleaned from a large number of endpoints (millions of computers), we can accomplish large-scale application identification automatically and reliably. Our approach relies on collecting metadata on billions of files every day, summarizing it into much smaller "sketches", and performing approximate k-nearest neighbor clustering on non-metric space representations derived from these sketches. We design and implement our proposed system using Apache Spark, show that it can process billions of files in a matter of hours, and thus could be used for daily processing. We further show our system manages to successfully identify which files belong to which application with very high precision, and adequate recall.

Mobile platforms, such as Android, warn users about the permissions an app requests and trust that the user will make the correct decision about whether or not to install the app. Unfortunately many users either ignore the warning or fail to understand the permissions and the risks they imply. As a step toward developing an indicator of risk that decomposes risk into several categories, or dimensions, we conducted two studies designed to assess the dimensions of risk deemed most important by experts and novices. In Study 1, semi-structured interviews were conducted with 19 security experts, who also performed a card sorting task in which they categorized permissions. The experts identified three major risk dimensions in the interviews (personal information privacy, monetary risk, and device availability/stability), and a forth dimension (data integrity) in the card sorting task. In Study 2, 350 typical Android users, recruited via Amazon Mechanical Turk, filled out a questionnaire in which they (a) answered questions concerning their mobile device usage, (b) rated how often they considered each of several types of information when installing apps, (c) indicated what they considered to be the biggest risk associated with installing an app on their mobile device, and (d) rated their concerns with regard to specific risk types and about apps having access to specific types of information. In general, the typical users' concerns were similar to those of the security experts. The results of the studies suggest that risk information should be organized into several risk types that can be better understood by users and that a mid-level risk summary should incorporate the dimensions of personal information privacy, monetary risk, device availability/stability risk and data integrity risk.

Mobile devices are an important part of our everyday lives, and the Android platform has become a market leader. In recent years a number of approaches for Android malware detection have been proposed, using permissions, source code analysis, or dynamic analysis. In this paper, we propose to use a probabilistic discriminative model based on regularized logistic regression for Android malware detection. Through extensive experimental evaluation, we demonstrate that it can generate probabilistic outputs with highly accurate classification results. In particular, we propose to use Android API calls as features extracted from decompiled source code, and analyze and explore issues in feature granularity, feature representation, feature selection, and regularization. We show that the probabilistic discriminative model also works well with permissions, and substantially outperforms the state-of-the-art methods for Android malware detection with application permissions. Furthermore, the discriminative learning model achieves the best detection results by combining both decompiled source code and application permissions. To the best of our knowledge, this is the first research that proposes probabilistic discriminative model for Android malware detection with a thorough study of desired representation of decompiled source code and is the first research work for Android malware detection task that combines both analysis of decompiled source code and application permissions.

The popularity and advanced functionality of mobile devices has made them attractive targets for malicious and intrusive applications (apps). Although strong security measures are in place for most mobile systems, the area where these systems often fail is the reliance on the user to make decisions that impact the security of a device. As our prime example, Android relies on users to understand the permissions that an app is requesting and to base the installation decision on the list of permissions. Previous research has shown that this reliance on users is ineffective, as most users do not understand or consider the permission information. We propose a solution that leverages a method to assign a risk score to each app and display a summary of that information to users. Results from four experiments are reported in which we examine the effects of introducing summary risk information and how best to convey such information to a user. Our results show that the inclusion of risk-score information has significant positive effects in the selection process and can also lead to more curiosity about security-related information.

One of Android's main defense mechanisms against malicious apps is a risk communication mechanism which, before a user installs an app, warns the user about the permissions the app requires, trusting that the user will make the right decision. This approach has been shown to be ineffective as it presents the risk information of each app in a “stand-alone” fashion and in a way that requires too much technical knowledge and time to distill useful information. We discuss the desired properties of risk signals and relative risk scores for Android apps in order to generate another metric that users can utilize when choosing apps. We present a wide range of techniques to generate both risk signals and risk scores that are based on heuristics as well as principled machine learning techniques. Experimental results conducted using real-world data sets show that these methods can effectively identify malware as very risky, are simple to understand, and easy to use.

Malware has been a major security problem both in organizations and homes for more than a decade. One common feature of most malware attacks is that at a certain point early in the attack, an executable is dropped on the system which, when executed, enables the attacker to achieve their goals and maintain control of the compromised machine. In this paper we propose the concept of Personalized Application Whitelisting (PAW) to block all unsolicited foreign code from executing on a system. We introduce CodeShield, an approach to implement PAW on Windows hosts. CodeShield uses a simple and novel security model, and a new user interaction approach for obtaining security-critical decisions from users. We have implemented CodeShield, demonstrated its security effectiveness, and conducted a user study, having 38 participants run CodeShield on their laptops for 6 weeks. Results from the data demonstrate the usability and promises of our design.

One of Android's main defense mechanisms against malicious apps is a risk communication mechanism which, before a user installs an app, warns the user about the permissions the app requires, trusting that the user will make the right decision. This approach has been shown to be ineffective as it presents the risk information of each app in a "tand-alone" ashion and in a way that requires too much technical knowledge and time to distill useful information.

The phenomenal growth of the Android platform in the past few years has made it a lucrative target of malicious application (app) developers. There are numerous instances of malware apps that send premium rate SMS messages, track users' private data, or apps that, even if not characterized as malware, conduct questionable actions affecting the user's privacy or costing them money. In this paper, we investigate the feasibility of using both the permissions an app requests, the category of the app, and what permissions are requested by other apps in the same category to better inform users whether the risks of installing an app is commensurate with its expected benefit. Existing approaches consider only the risks of the permissions requested by an app and ignore both the benefits and what permissions are requested by other apps, thus having a limited effect. We propose several risk signals that and evaluate them using two datasets, one consists of 158,062 Android apps from the Android Market, and another consists of 121 malicious apps. We demonstrate the effectiveness of our proposal through extensive data analysis.

An operating system relies heavily on its access control mechanisms to defend against local and remote attacks. The complexities of modern access control mechanisms and the scale of possible configurations are often overwhelming to system administrators and software developers. Therefore mis-configurations are very common and the security consequences are serious. Given the popularity and uniqueness of Microsoft Windows systems, it is critical to have a tool to comprehensively examine the access control configurations. However, current studies on Windows access control mechanisms are mostly based on known attack patterns. We propose a tool, WACCA, to systematically analyze the Windows configurations. Given the attacker's initial abilities and goals, WACCA generates an attack graph based on interaction rules. The tool then automatically generates attack patterns from the attack graph. Each attack pattern represents attacks of the same nature. The attack subgraphs and instances are also generated for each pattern. Compared to existing solutions, WACCA is more comprehensive and does not rely on manually defined attack patterns. It also has a unique feature in that it models software vulnerabilities and therefore can find attacks that rely on exploiting these vulnerabilities. We study two attack cases on a Windows Vista host and discuss the analysis results.