Kevin Alejandro Roundy

Kevin Alejandro Roundy

Kevin Alejandro Roundy

Dr. Kevin Roundy joined the research group after receiving his Ph.D. from the University of Wisconsin in 2012.

As a graduate student, he developed tools by which obfuscated malware could be analyzed both with detailed static analysis techniques and dynamic instrumentation. Kevin has collaboratively developed broadly deployed threat-detection tools.

He has also worked in Endpoint Detection and Response on risk modeling. Additional areas of current interest include human-centric security and privacy paradigms. During his time with the company, Kevin has authored several research publications and patents. Kevin has a background in Machine Learning and Database systems, and did his undergraduate work at Brigham Young University.

Selected Academic Papers

A Field Study of Computer-Security Perceptions Using Anti-Virus Customer-Support Chats

In Proceedings of the 2019 Conference on Human Factors in Computing Systems (CHI 2019)
To identify needs for improvement in security products, we study security concerns raised in Norton Security customer support chats. We found that many consumers face technical support scams and are susceptible to them. Findings also show the value of customer support centers in that 96% of customers that reach out for support in relation to scams have not paid the scammers

Examining the Adoption and Abandonment of Security, Privacy, and Identity Theft Protection Practices

In Proceedings of ACM CHI Conference on Human Factors in Computing Systems (CHI 2020) (Honorable Mention Award)
Our online survey of 902 individuals studies the reasons for which users struggle to adhere to expert-recommended security, privacy, and identity-protection practices. We examined 30 of these practices, finding that gender, education, technical background, and prior negative experiences correlate with practice adoption levels. We found that practices were abandoned when they were perceived as low-value, inconvenient, or when overridden by subjective judgment. We discuss how tools and expert recommendations can better align to user needs.

Automatic Application Identification from Billions of Files

In Proceedings of the 23rd SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2017)
Mapping binary files into software packages enables malware detection and other tasks, but is challenging. By combining installation data with file metadata that we summarize into sketches, from millions of machines and billions of files, we can use efficient approximate clustering techniques to map files to applications automatically and reliably.

Making Machine Learning Forget

In Proceedings of the 2019 ENISA Annual Privacy Forum (APF 2019)
We specifically analyze how the “right-to-be-forgotten” provided by the European Union General Data Protection Regulation can be implemented on current machine learning models and which techniques can be used to build future models that can forget. This document also serves as a call-to-action for researchers and policy-makers to identify other technologies that can be used for this purpose.

Hierarchical Incident Clustering for Security Operation Centers

In Proceedings of the Interactive Data Exploration and Analytics Workshop (IDEA 2018)
We enable security incident responders to dispatch multiple similar security incidents at once through an intuitive user interface. The heart of our algorithm is a visualized hierarchical clustering technique that enables responders to identify the appropriate level of cluster granularity at which to dispatch multiple incidents.

Generating Graph Snapshots from Streaming Edge Data

In Proceedings of the 25th International World Wide Web Conference (WWW), 2016
We study the problem of determining the proper aggregation granularity for a stream of time-stamped edges. To this end, we propose ADAGE and demonstrate its value in automatically finding the appropriate aggregation intervals on edge streams for belief propagation to detect malicious files and machines.

VIGOR: Interactive Visual Exploration of Graph Query Results

IEEE Transactions on Visualization and Computer Graphics (TVCG), 24(1), 2018, Presented at the 2017 IEEE Conference on Visual Analytics Science and Technology (VAST), 2017
We present VIGOR, a novel interactive visual analytics system, for exploring and making sense of graph query results. VIGOR contributes an exemplar-based interaction technique and a feature-aware subgraph result summarization. Through a collaboration with Symantec, we demonstrate how VIGOR helps tackle real-world cybersecurity problems.

Collaborative and Privacy-Preserving Machine Teaching via Consensus Optimization

In Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN 2019)
In this work, we define a collaborative and privacy-preserving machine teaching paradigm with multiple distributed teachers. The focus is to find strategies to organize distributed agents to jointly select a compact subset of data that can be used to train a global model. The global model should achieve nearly the same performance as if the central learner had access to all the data, but the central learner only has access to the selected subset, and each agent only has access to their own data. The goal of this research is to find good strategies to train global models while giving some control back to agents.

Large-Scale Identification of Malicious Singleton Files

In Proceedings of the 7th ACM Conference on Data and Application Security and Privacy (CODASPY)
94% of the software files that Symantec saw in a 1-year dataset appeared only once on a single machine. We examine the primary reasons for which both benign and malicious software files appear as singletons, and design a classifier to distinguish between these two classes of singleton software files.

Smoke Detector: Cross-Product Intrusion Detection With Weak Indicators

In Proceedings of the Annual Computer Security Applications Conference (ACSAC 2017)
Smoke Detector significantly expands upon limited collections of hand-labeled security incidents by framing event data as relationships between events and machines, and performing random walks to rank candidate security incidents. Smoke Detector significantly increases incident detection coverage for mature Managed Security Service Providers.

Predicting Cyber Threats with Virtual Security Products

In Proceedings of the 33th Annual computer Security Applications Conference (ACSAC 2017)
We set out to predict which security events and incidents a security product would have detected had it been deployed, based on the events produced by other security products that were in place. We discovered that the problem is tractable, and that some security products are much harder to model than others, which makes them more valuable.

The Many Kinds of Creepware Used for Interpersonal Attacks

In Proceedings of the 41st IEEE Symposium on Security and Privacy (S&P 2020)
Technology increasingly facilitates interpersonal attacks such as stalking, abuse, and other forms of harassment. While prior studies have examined the ecosystem of software designed for stalking, our study uncovers a larger landscape of apps---what we call creepware---used for interpersonal attacks. We discover and report on apps used for harassment, impersonation, fraud, information theft, concealment, hacking, and other attacks, as well as creative defensive apps that victims use to protect themselves.

Training Older Adults to Resist Scams with Fraud Bingo and Scam Detection Challenges

In Proceedings of the 2020 CHI Workshop on Designing Interactions for the Ageing Populations - Addressing Global Challenges
Older adults are disproportionately affected by scams, many of which target them specifically. We present Fraud Bingo, an intervention designed by WISE \& Healthy Aging Center in Southern California prior to 2012, that has been played by older adults throughout the United States. We also present the Scam Defender Obstacle Course (SDOC), an interactive web application that tests a user's ability to identify scams, and subsequently teaches them how to recognize the scams. SDOC is patterned after existing phishing-recognition training tools for working professionals. We present the results of running a workshop with 17 senior citizens, where we performed a controlled study that and used SDOC to measure the effectiveness of Fraud Bingo. We outline the difficulties several participants had with completing SDOC, which indicate that tools like SDOC should be tailored to the needs of older adults.

The Role of Computer Security Customer Support in Helping Survivors of Intimate Partner Violence

In Proceedings of the 30th USENIX Security Symposium (USENIX Security 2021)

Towards Stalkerware Detection with Precise Warnings

In Proceedings of the 37th Annual Computer Security Applications Conference (ACSAC 2021)

Trauma-Informed Computing: Towards Safer Technology Experiences for All

In Proceedings of the 2022 Conference on Human Factors in Computing Systems (CHI 2022)