arXiv subjects

Gene Tsudik

Publications and source records attributed to Gene Tsudik.

At least 19 recordsLinked to original sources

arXiv2026

What's on Your Mind? Exploring Privacy of Mental Health Apps

Therapy and life-coaching apps have grown rapidly in number, variety, and popularity. At the same time, their users often share highly sensitive and personal information, including mental health issues, trauma experiences, fantasies, desires, and relationship difficulties. This prompts the need to examine privacy practices across the ecosystem. In this paper, we present a comprehensive analysis of a corpus of 25 popular Android mental health and life-coaching apps, such as Replika and Headspace. It builds on static analysis and dynamic network traffic analysis, coupled with identifying gaps between each app's observed behavior and its privacy policies. Our analysis highlights serious concerns and substantial transparency gaps. First, every app in our corpus embeds at least one tracker SDK not named in its privacy policy, and 85\% of the apps we instrument fail to disclose at least half of the trackers detected in their APKs. Second, more than half of the apps declare several dangerous permissions without corresponding privacy-policy disclosures, including camera or microphone permissions. Third, nearly half the apps disclose third-party AI processing (e.g., via OpenAI, Anthropic, and Groq) in their privacy policies, while several use only generic language (e.g., "AI services"), failing to identify which company receives user data. Overall, our results show that current disclosure practices fall short of the transparency needed for meaningful informed consent. We argue for a significantly updated regulatory framework for therapy apps that more closely aligns with the professional and ethical standards that bind licensed human therapists.

cs.CR↗

arXiv2026

Let My Data Go: Data Brokers' Compliance with Opt-Out and Deletion Requests

Data brokers are a largely American phenomenon. They collect vast amounts of personal information about most adult U.S. consumers, mainly without the latter's knowledge or consent. Accumulated data can be sold to anyone, including employers, landlords, insurance agencies, banks, governments (local, state, federal, and even foreign), as well as various malicious actors. This, in turn, enables discrimination, surveillance, identity theft, and stalking. Recent regulations -- such as the California Consumer Privacy Act (CCPA) modeled after EU's General Data Protection Regulation (GDPR) -- were introduced to bolster consumer privacy, e.g., the rights to: (1) opt-out of the sharing or selling one's personal information, (2) delete one's personal information, and (3) obtain a copy of that information. However, exercising these rights is not easy, as shown by our comprehensive study of the data broker ecosystem. We submitted both opt-out and deletion requests (using synthetic consumer identities) under the CCPA to all California-registered data brokers and investigated their responses and lack thereof. While the majority seem to be compliant, a significant fraction is not and many failed to reply to (and/or acknowledge) consumer requests. Furthermore, some data brokers require intrusive consumer identity verification in order to exercise one's opt-out rights, which is explicitly disallowed by the CCPA. There is also great disparity in the request submission process among data brokers as well as an extremely heavy (time and effort) overall consumer burden. This motivates an urgent need for streamlining and standardization of the consumer interface, stronger enforcement, and meaningful consequences for (especially sustained) non-compliance.

cs.CR↗

arXiv2026

DuoLungo: Usability Study of Duo 2FA

Multi-Factor Authentication (MFA) enhances login security by requiring multiple authentication factors. Its adoption has increased in response to more frequent and sophisticated attacks. Duo is widely used by organizations including Fortune 500 companies and major educational institutions, yet its usability has not been examined thoroughly or recently. Earlier studies focused on technical challenges during initial deployment but did not measure core usability metrics such as task completion time or System Usability Scale (SUS) scores. These results are also outdated, originating from a time when MFA was less familiar to typical users. We conducted a long-term, large-scale Duo usability study at the University of California Irvine during the 2024-2025 academic year, involving 2559 participants. Our analysis uses authentication log data and a survey of 57 randomly selected users. The average overhead of a Duo Push task is nearly 8 seconds, which participants described as short to moderate. Overhead varies with time of day, field of study, and education level. The rate of authentication failures due to incomplete Duo tasks is 4.35 percent, and 43.86 percent of survey respondents reported at least one Duo login failure. The Duo SUS score is 70, indicating good usability. Participants generally find Duo easy to use but somewhat annoying, while also reporting an increased sense of account security. They also described common issues and offered suggestions for improvement.

cs.CR↗

arXiv2025

Consumer Beware! Exploring Data Brokers' CCPA Compliance

Data brokers collect and sell the personal information of millions of individuals, often without their knowledge or consent. The California Consumer Privacy Act (CCPA) grants consumers the legal right to request access to, or deletion of, their data. To facilitate these requests, California maintains an official registry of data brokers. However, the extent to which these entities comply with the law is unclear. This paper presents the first large-scale, systematic study of CCPA compliance of all 543 officially registered data brokers. Data access requests were manually submitted to each broker, followed by in-depth analyses of their responses (or lack thereof). Above 40% failed to respond at all, in an apparent violation of the CCPA. Data brokers that responded requested personal information as part of their identity verification process, including details they had not previously collected. Paradoxically, this means that exercising one's privacy rights under CCPA introduces new privacy risks. Our findings reveal rampant non-compliance and lack of standardization of the data access request process. These issues highlight an urgent need for stronger enforcement, clearer guidelines, and standardized, periodic compliance checks to enhance consumers' privacy protections and improve data broker accountability.

cs.CR↗

arXiv2025

Oblivious Digital Tokens

A computing device typically identifies itself by exhibiting unique measurable behavior or by proving its knowledge of a secret. In both cases, the identifying device must reveal information to a verifier. Considerable research has focused on protecting identifying entities (provers) and reducing the amount of leaked data. However, little has been done to conceal the fact that the verification occurred. We show how this problem naturally arises in the context of digital emblems, which were recently proposed by the International Committee of the Red Cross to protect digital resources during cyber-conflicts. To address this new and important open problem, we define a new primitive, called an Oblivious Digital Token (ODT) that can be verified obliviously. Verifiers can use this procedure to check whether a device has an ODT without revealing to any other parties (including the device itself) that this check occurred. We demonstrate the feasibility of ODTs and present a concrete construction that provably meets the ODT security requirements, even if the prover device's software is fully compromised. We also implement a prototype of the proposed construction and evaluate its performance, thereby confirming its practicality.

cs.CR↗

arXiv2025

SoK: Decoding the Enigma of Encrypted Network Traffic Classifiers

The adoption of modern encryption protocols such as TLS 1.3 has significantly challenged traditional network traffic classification (NTC) methods. As a consequence, researchers are increasingly turning to machine learning (ML) approaches to overcome these obstacles. In this paper, we comprehensively analyze ML-based NTC studies, developing a taxonomy of their design choices, benchmarking suites, and prevalent assumptions impacting classifier performance. Through this systematization, we demonstrate widespread reliance on outdated datasets, oversights in design choices, and the consequences of unsubstantiated assumptions. Our evaluation reveals that the majority of proposed encrypted traffic classifiers have mistakenly utilized unencrypted traffic due to the use of legacy datasets. Furthermore, by conducting 348 feature occlusion experiments on state-of-the-art classifiers, we show how oversights in NTC design choices lead to overfitting, and validate or refute prevailing assumptions with empirical evidence. By highlighting lessons learned, we offer strategic insights, identify emerging research directions, and recommend best practices to support the development of real-world applicable NTC methodologies.

cs.CR↗

arXiv2025

Acoustic Side-Channel Attacks on a Computer Mouse

Acoustic Side-Channel Attacks (ASCAs) extract sensitive information by using audio emitted from a computing devices and their peripherals. Attacks targeting keyboards are popular and have been explored in the literature. However, similar attacks targeting other human interface peripherals, such as computer mice, are under-explored. To this end, this paper considers security leakage via acoustic signals emanating from normal mouse usage. We first confirm feasibility of such attacks by showing a proof-of-concept attack that classifies four mouse movements with 97% accuracy in a controlled environment. We then evolve the attack towards discerning twelve unique mouse movements using a smartphone to record the experiment. Using Machine Learning (ML) techniques, the model is trained on an experiment with six participants to be generalizable and discern among twelve movements with 94% accuracy. In addition, we experiment with an attack that detects a user action of closing a full-screen window on a laptop. Achieving an accuracy of 91%, this experiment highlights exploiting audio leakage from computer mouse movements in a realistic scenario.

cs.CR↗

arXiv2025

URL Inspection Tasks: Helping Users Detect Phishing Links in Emails

The most widespread type of phishing attack involves email messages with links pointing to malicious content. Despite user training and the use of detection techniques, these attacks are still highly effective. Recent studies show that it is user inattentiveness, rather than lack of education, that is one of the key factors in successful phishing attacks. To this end, we develop a novel phishing defense mechanism based on URL inspection tasks: small challenges (loosely inspired by CAPTCHAs) that, to be solved, require users to interact with, and understand, the basic URL structure. We implemented and evaluated three tasks that act as ``barriers'' to visiting the website: (1) correct click-selection from a list of URLs, (2) mouse-based highlighting of the domain-name URL component, and (3) re-typing the domain-name. These tasks follow best practices in security interfaces and warning design. We assessed the efficacy of these tasks through an extensive on-line user study with 2,673 participants from three different cultures, native languages, and alphabets. Results show that these tasks significantly decrease the rate of successful phishing attempts, compared to the baseline case. Results also showed the highest efficacy for difficult URLs, such as typo-squats, with which participants struggled the most. This highlights the importance of (1) slowing down users while focusing their attention and (2) helping them understand the URL structure (especially, the domain-name component thereof) and matching it to their intent.

cs.CR↗

arXiv2025

MADEA: A Malware Detection Architecture for IoT blending Network Monitoring and Device Attestation

Internet-of-Things (IoT) devices are vulnerable to malware and require new mitigation techniques due to their limited resources. To that end, previous research has used periodic Remote Attestation (RA) or Traffic Analysis (TA) to detect malware in IoT devices. However, RA is expensive, and TA only raises suspicion without confirming malware presence. To solve this, we design MADEA, the first system that blends RA and TA to offer a comprehensive approach to malware detection for the IoT ecosystem. TA builds profiles of expected packet traces during benign operations of each device and then uses them to detect malware from network traffic in real-time. RA confirms the presence or absence of malware on the device. MADEA achieves 100% true positive rate. It also outperforms other approaches with 160x faster detection time. Finally, without MADEA, effective periodic RA can consume at least ~14x the amount of energy that a device needs in one hour.

cs.CR↗

arXiv2025

TOCTOU Resilient Attestation for IoT Networks (Full Version)

Internet-of-Things (IoT) devices are increasingly common in both consumer and industrial settings, often performing safety-critical functions. Although securing these devices is vital, manufacturers typically neglect security issues or address them as an afterthought. This is of particular importance in IoT networks, e.g., in the industrial automation settings. To this end, network attestation -- verifying the software state of all devices in a network -- is a promising mitigation approach. However, current network attestation schemes have certain shortcomings: (1) lengthy TOCTOU (Time-Of-Check-Time-Of-Use) vulnerability windows, (2) high latency and resource overhead, and (3) susceptibility to interference from compromised devices. To address these limitations, we construct TRAIN (TOCTOU-Resilient Attestation for IoT Networks), an efficient technique that minimizes TOCTOU windows, ensures constant-time per-device attestation, and maintains resilience even with multiple compromised devices. We demonstrate TRAIN's viability and evaluate its performance via a fully functional and publicly available prototype.

cs.CR↗

arXiv2025

EILID: Execution Integrity for Low-end IoT Devices

Prior research yielded many techniques to mitigate software compromise for low-end Internet of Things (IoT) devices. Some of them detect software modifications via remote attestation and similar services, while others preventatively ensure software (static) integrity. However, achieving run-time (dynamic) security, e.g., control-flow integrity (CFI), remains a challenge. Control-flow attestation (CFA) is one approach that minimizes the burden on devices. However, CFA is not a real-time countermeasure against run-time attacks since it requires communication with a verifying entity. This poses significant risks if safety- or time-critical tasks have memory vulnerabilities. To address this issue, we construct EILID - a hybrid architecture that ensures software execution integrity by actively monitoring control-flow violations on low-end devices. EILID is built atop CASU, a prevention-based (i.e., active) hybrid Root-of-Trust (RoT) that guarantees software immutability. EILID achieves fine-grained backward-edge and function-level forward-edge CFI via semi-automatic code instrumentation and a secure shadow stack.

cs.CR↗

arXiv2024

DB-PAISA: Discovery-Based Privacy-Agile IoT Sensing+Actuation

Internet of Things (IoT) devices are becoming increasingly commonplace in numerous public and semi-private settings. Currently, most such devices lack mechanisms to facilitate their discovery by casual (nearby) users who are not owners or operators. However, these users are potentially being sensed, and/or actuated upon, by these devices, without their knowledge or consent. This naturally triggers privacy, security, and safety issues. To address this problem, some recent work explored device transparency in the IoT ecosystem. The intuitive approach is for each device to periodically and securely broadcast (announce) its presence and capabilities to all nearby users. While effective, when no new users are present, this push-based approach generates a substantial amount of unnecessary network traffic and needlessly interferes with normal device operation. In this work, we construct DB-PAISA which addresses these issues via a pull-based method, whereby devices reveal their presence and capabilities only upon explicit user request. Each device guarantees a secure timely response (even if fully compromised by malware) based on a small active Root-of-Trust (RoT). DB-PAISA requires no hardware modifications and is suitable for a range of current IoT devices. To demonstrate its feasibility and practicality, we built a fully functional and publicly available prototype. It is implemented atop a commodity MCU (NXP LCP55S69) and operates in tandem with a smartphone-based app. Using this prototype, we evaluate energy consumption and other performance factors.

cs.CR↗

arXiv2024

KESIC: Kerberos Extensions for Smart, IoT and CPS Devices

Secure and efficient multi-user access mechanisms are increasingly important for the growing number of Internet of Things (IoT) devices being used today. Kerberos is a well-known and time-tried security authentication and access control system for distributed systems wherein many users securely access various distributed services. Traditionally, these services are software applications or devices, such as printers. However, Kerberos is not directly suitable for IoT devices due to its relatively heavy-weight protocols and the resource-constrained nature of the devices. This paper presents KESIC, a system that enables efficient and secure multi-user access for IoT devices. KESIC aims to facilitate mutual authentication of IoT devices and users via Kerberos without modifying the latter's protocols. To facilitate that, KESIC includes a special Kerberized service, called IoT Server, that manages access to IoT devices. KESIC presents two protocols for secure and comprehensive multi-user access system for two types of IoT devices: general and severely power constrained. In terms of performance, KESIC onsumes $\approx~47$ times less memory, and incurs $\approx~135$ times lower run-time overhead than Kerberos.

cs.CR↗

arXiv2024

Towards Remotely Verifiable Software Integrity in Resource-Constrained IoT Devices

Lower-end IoT devices typically have strict cost constraints that rule out usual security mechanisms available in general-purpose computers or higher-end devices. To secure low-end devices, various low-cost security architectures have been proposed for remote verification of their software state via integrity proofs. These proofs vary in terms of expressiveness, with simpler ones confirming correct binary presence, while more expressive ones support verification of arbitrary code execution. This article provides a holistic and systematic treatment of this family of architectures. It also compares (qualitatively and quantitatively) the types of software integrity proofs, respective architectural support, and associated costs. Finally, we outline some research directions and emerging challenges.

cs.CR↗

arXiv2023

Puppy: A Publicly Verifiable Watermarking Protocol

In this paper, we propose Puppy, the first formally defined framework for converting any symmetric watermarking into a publicly verifiable one. Puppy allows anyone to verify a watermark any number of times with the help of an untrusted third party, without requiring owner presence during detection. We formally define and prove security of Puppy using the ideal/real-world simulation paradigm and construct two practical and secure instances: (1) Puppy-TEE that uses Trusted Execution Environments (TEEs), and (2) Puppy-2PC that relies on two-party computation (2PC) based on garbled circuits. We then convert four current symmetric watermarking schemes into publicly verifiable ones and run extensive experiments using Puppy-TEE and Puppy-2PC. Evaluation results show that, while Puppy-TEE incurs some overhead, its total latency is on the order of milliseconds for three out of four watermarking schemes. Although the overhead of Puppy-2PC is higher (on the order of seconds), it is viable for settings that lack a TEE or where strong trust assumptions about a TEE need to be avoided. We further optimize the solution to increase its scalability and resilience to denial of service attacks via memoization.

cs.CR↗

arXiv2023

Dazed & Confused: A Large-Scale Real-World User Study of reCAPTCHAv2

Since about 2003, captchas have been widely used as a barrier against bots, while simultaneously annoying great multitudes of users worldwide. As their use grew, techniques to defeat or bypass captchas kept improving, while captchas themselves evolved in terms of sophistication and diversity, becoming increasingly difficult to solve for both bots and humans. Given this long-standing and still-ongoing arms race, it is important to investigate usability, solving performance, and user perceptions of modern captchas. In this work, we do so via a large-scale (over 3, 600 distinct users) 13-month real-world user study and post-study survey. The study, conducted at a large public university, was based on a live account creation and password recovery service with currently prevalent captcha type: reCAPTCHAv2. Results show that, with more attempts, users improve in solving checkbox challenges. For website developers and user study designers, results indicate that the website context directly influences (with statistically significant differences) solving time between password recovery and account creation. We consider the impact of participants' major and education level, showing that certain majors exhibit better performance, while, in general, education level has a direct impact on solving time. Unsurprisingly, we discover that participants find image challenges to be annoying, while checkbox challenges are perceived as easy. We also show that, rated via System Usability Scale (SUS), image tasks are viewed as "OK", while checkbox tasks are viewed as "good". We explore the cost and security of reCAPTCHAv2 and conclude that it has an immense cost and no security. Overall, we believe that this study's results prompt a natural conclusion: reCAPTCHAv2 and similar reCAPTCHA technology should be deprecated.

cs.CR↗

arXiv2023

Poster: Control-Flow Integrity in Low-end Embedded Devices

Embedded, smart, and IoT devices are increasingly popular in numerous everyday settings. Since lower-end devices have the most strict cost constraints, they tend to have few, if any, security features. This makes them attractive targets for exploits and malware. Prior research proposed various security architectures for enforcing security properties for resource-constrained devices, e.g., via Remote Attestation (RA). Such techniques can (statically) verify software integrity of a remote device and detect compromise. However, run-time (dynamic) security, e.g., via Control-Flow Integrity (CFI), is hard to achieve. This work constructs an architecture that ensures integrity of software execution against run-time attacks, such as Return-Oriented Programming (ROP). It is built atop a recently proposed CASU -- a low-cost active Root-of-Trust (RoT) that guarantees software immutability. We extend CASU to support a shadow stack and a CFI monitor to mitigate run-time attacks. This gives some confidence that CFI can indeed be attained even on low-end devices, with minimal hardware overhead.

cs.CR↗

arXiv2023

Caveat (IoT) Emptor: Towards Transparency of IoT Device Presence (Full Version)

As many types of IoT devices worm their way into numerous settings and many aspects of our daily lives, awareness of their presence and functionality becomes a source of major concern. Hidden IoT devices can snoop (via sensing) on nearby unsuspecting users, and impact the environment where unaware users are present, via actuation. This prompts, respectively, privacy and security/safety issues. The dangers of hidden IoT devices have been recognized and prior research suggested some means of mitigation, mostly based on traffic analysis or using specialized hardware to uncover devices. While such approaches are partially effective, there is currently no comprehensive approach to IoT device transparency. Prompted in part by recent privacy regulations (GDPR and CCPA), this paper motivates and constructs a privacy-agile Root-of-Trust architecture for IoT devices, called PAISA: Privacy-Agile IoT Sensing and Actuation. It guarantees timely and secure announcements about IoT devices' presence and their capabilities. PAISA has two components: one on the IoT device that guarantees periodic announcements of its presence even if all device software is compromised, and the other that runs on the user device, which captures and processes announcements. Notably, PAISA requires no hardware modifications; it uses a popular off-the-shelf Trusted Execution Environment (TEE) -- ARM TrustZone. This work also comprises a fully functional (open-sourced) prototype implementation of PAISA, which includes: an IoT device that makes announcements via IEEE 802.11 WiFi beacons and an Android smartphone-based app that captures and processes announcements. Both security and performance of PAISA design and prototype are discussed.

cs.CR↗