L. Jean Camp

Dalyapraz Manatova, Pablo Moriano, L. Jean Camp

Graph neural networks (GNNs) are designed to use attributed graphs to learn representations. Such representations are beneficial in the unsupervised learning of clusters and community detection. Nonetheless, such inference may reveal sensitive groups, clustered systems, or collective behaviors, raising concerns regarding group-level privacy. Community attribution in social and critical infrastructure networks, for example, can expose coordinated asset groups, operational hierarchies, and system dependencies that could be used for profiling or intelligence gathering. We study a defensive setting in which a data publisher (defender) seeks to conceal a community of interest while making limited, utility-aware changes in the network. Our analysis indicates that community concealment is strongly influenced by two quantifiable factors: connectivity at the community boundary and feature similarity between the protected community and adjacent communities. Informed by these findings, we present a perturbation strategy that rewires a set of selected edges and modifies node features to reduce the distinctiveness leveraged by GNN message passing. The proposed method outperforms DICE in our experiments on synthetic benchmarks and real network graphs under identical perturbation budgets. Overall, it achieves median relative concealment improvements of approximately 20-45% across the evaluated settings. These findings demonstrate a mitigation strategy against GNN-based community learning and highlight group-level privacy risks intrinsic to graph learning.

Xinyao Ma, Rui Zhu, Zihao Wang et al.

Large Language Models (LLMs) have demonstrated impressive capabilities in role-playing scenarios, particularly in simulating domain-specific experts using tailored prompts. This ability enables LLMs to adopt the persona of individuals with specific backgrounds, offering a cost-effective and efficient alternative to traditional, resource-intensive user studies. By mimicking human behavior, LLMs can anticipate responses based on concrete demographic or professional profiles. In this paper, we evaluate the effectiveness of LLMs in simulating individuals with diverse backgrounds and analyze the consistency of these simulated behaviors compared to real-world outcomes. In particular, we explore the potential of LLMs to interpret and respond to discharge summaries provided to patients leaving the Intensive Care Unit (ICU). We evaluate and compare with human responses the comprehensibility of discharge summaries among individuals with varying educational backgrounds, using this analysis to assess the strengths and limitations of LLM-driven simulations. Notably, when LLMs are primed with educational background information, they deliver accurate and actionable medical guidance 88% of the time. However, when other information is provided, performance significantly drops, falling below random chance levels. This preliminary study shows the potential benefits and pitfalls of automatically generating patient-specific health information from diverse populations. While LLMs show promise in simulating health personas, our results highlight critical gaps that must be addressed before they can be reliably used in clinical settings. Our findings suggest that a straightforward query-response model could outperform a more tailored approach in delivering health information. This is a crucial first step in understanding how LLMs can be optimized for personalized health communication while maintaining accuracy.

Vafa Andalibi, Jayati Dev, DongInn Kim et al.

Secure installation of Internet of Things (IoT) devices requires configuring access control correctly for each device. In order to enable correct configuration the Manufacturer Usage Description (MUD) has been developed by Internet Engineering Task Force (IETF) to automate the protection of IoT devices by micro-segmentation using dynamic access control lists. The protocol defines a conceptually straightforward method to implement access control upon installation by providing a list of every authorized access for each device. This access control list may contain a few rules or hundreds of rules for each device. As a result, validating these rules is a challenge. In order to make the MUD standard more usable for developers, system integrators, and network operators, we report on an interactive system called MUD-Visualizer that visualizes the files containing these access control rules. We show that, unlike manual analysis, the level of the knowledge and experience does not affect the accuracy of the analysis when MUD-Visualizer is used, indicating that the tool is effective for all participants in our study across knowledge and experience levels.

Vafa Andalibi, Eliot Lear, DongInn Kim et al.

Manufacturer Usage Description (MUD) is an Internet Engineering Task Force (IETF) standard designed to protect IoT devices and networks by creating an out-of-the-box access control list for an IoT device. %The protocol defines a conceptually straightforward method to implement an isolation-based defensive mechanism based on the rules that are introduced by the manufacturer of the device. However, in practice, the access control list of each device is defined in its MUD-File and may contain possibly hundreds of access control rules. As a result, reading and validating these files is a challenge; and determining how multiple IoT devices interact is difficult for the developer and infeasible for the consumer. To address this we introduce the MUD-Visualizer to provide a visualization of any number of MUD-Files. MUD-Visualizer is designed to enable developers to produce correct MUD-Files by providing format correction, integrating them with other MUD-Files, and identifying conflicts through visualization. MUD-Visualizer is scalable and its core task is to merge and illustrate ACEs for multiple devices; both within and beyond the local area network. MUD-Visualizer is made publicly available and can be found on GitHub.

Sanchari Das, Robert S. Gutzwiller, Rod D. Roscoe et al.

Computer security and user privacy are critical issues and concerns in the digital era due to both increasing users and threats to their data. Separate issues arise between generic cybersecurity guidance (i.e., protect all user data from malicious threats) and the individualistic approach of privacy (i.e., specific to users and dependent on user needs and risk perceptions). Research has shown that several security- and privacy-focused vulnerabilities are technological (e.g., software bugs (Streiff, Kenny, Das, Leeth, & Camp, 2018), insecure authentication (Das, Wang, Tingle, & Camp, 2019)), or behavioral (e.g., sharing passwords (Das, Dingman, & Camp, 2018); and compliance (Das, Dev, & Srinivasan, 2018) (Dev, Das, Rashidi, & Camp, 2019)). This panel proposal addresses a third category of sociotechnical vulnerabilities that can and sometimes do arise from non-inclusive design of security and privacy. In this panel, we will address users' needs and desires for privacy. The panel will engage in in-depth discussions about value-sensitive design while focusing on potentially vulnerable populations, such as older adults, teens, persons with disabilities, and others who are not typically emphasized in general security and privacy concerns. Human factors have a stake in and ability to facilitate improvements in these areas.

Ploy Unchit, Sanchari Das, Andrew Kim et al.

Spear phishing is a deceptive attack that uses social engineering to obtain confidential information through targeted victimization. It is distinguished by its use of social cues and personalized information to target specific victims. Previous work on resilience to spear phishing has focused on convenience samples, with a disproportionate focus on students. In contrast, here, we report on an evaluation of a high school community. We engaged 57 high school students and faculty members (12 high school students, 45 staff members) as participants in research utilizing signal detection theory (SDT). Through scenario-based analysis, participants tasked with distinguishing phishing emails from authentic emails. The results revealed an overconfidence bias in self-detection from the participants, regardless of their technical background. These findings are critical for evaluating the decision-making of underrepresented populations and protecting people from potential spear phishing attacks by examining human susceptibility.

Sanchari Das, Bingxing Wang, L. Jean Camp

Traditional single-factor authentication possesses several critical security vulnerabilities due to single-point failure feature. Multi-factor authentication (MFA), intends to enhance security by providing additional verification steps. However, in practical deployment, users often experience dissatisfaction while using MFA, which leads to non-adoption. In order to understand the current design and usability issues with MFA, we analyze aggregated user generated comments (N = 12,500) about application-based MFA tools from major distributors, such as, Amazon, Google Play, Apple App Store, and others. While some users acknowledge the security benefits of MFA, majority of them still faced problems with initial configuration, system design understanding, limited device compatibility, and risk trade-offs leading to non-adoption of MFA. Based on these results, we provide actionable recommendations in technological design, initial training, and risk communication to improve the adoption and user experience of MFA.

Sanchari Das, Bingxing Wang, Zachary Tingle et al.

Security vulnerabilities of traditional single factor authentication has become a major concern for security practitioners and researchers. To mitigate single point failures, new and technologically advanced Multi-Factor Authentication (MFA) tools have been developed as security solutions. However, the usability and adoption of such tools have raised concerns. An obvious solution can be viewed as conducting user studies to create more user-friendly MFA tools. To learn more, we performed a systematic literature review of recently published academic papers (N = 623) that primarily focused on MFA technologies. While majority of these papers (m = 300) proposed new MFA tools, only 9.1% of papers performed any user evaluation research. Our meta-analysis of user focused studies (n = 57) showed that researchers found lower adoption rate to be inevitable for MFAs, while avoidance was pervasive among mandatory use. Furthermore, we noted several reporting and methodological discrepancies in the user focused studies. We identified trends in participant recruitment that is indicative of demographic biases.

Pablo Moriano, Raquel Hill, L. Jean Camp

Despite the robust structure of the Internet, it is still susceptible to disruptive routing updates that prevent network traffic from reaching its destination. Our research shows that BGP announcements that are associated with disruptive updates tend to occur in groups of relatively high frequency, followed by periods of infrequent activity. We hypothesize that we may use these bursty characteristics to detect anomalous routing incidents. In this work, we use manually verified ground truth metadata and volume of announcements as a baseline measure, and propose a burstiness measure that detects prior anomalous incidents with high recall and better precision than the volume baseline. We quantify the burstiness of inter-arrival times around the date and times of four large-scale incidents: the Indosat hijacking event in April 2014, the Telecom Malaysia leak in June 2015, the Bharti Airtel Ltd. hijack in November 2015, and the MainOne leak in November 2018; and three smaller scale incidents that led to traffic interception: the Belarusian traffic direction in February 2013, the Icelandic traffic direction in July 2013, and the Russian telecom that hijacked financial services in April 2017. Our method leverages the burstiness of disruptive update messages to detect these incidents. We describe limitations, open challenges, and how this method can be used for routing anomaly detection.