arXiv subjects

Athina Markopoulou

Publications and source records attributed to Athina Markopoulou.

At least 19 recordsLinked to original sources

arXiv2026

PromptPET: Privacy-Utility Optimized Prompt Obfuscation

Privacy is an important challenge when users interact with AI chatbots, since users may share sensitive information, explicitly or implicitly, and AI chatbots can use this information for user profiling. In this paper, we aim to protect user privacy via a user-side mechanism that transforms sensitive information in a user prompt, while preserving enough information to elicit a useful response from the chatbot. This approach faces an inherent tradeoff between protecting privacy (i.e., avoiding profiling) and preserving utility (i.e., getting personalized and task-specific responses). To that end, we consider, evaluate, and compare four different obfuscation actions, namely redaction, abstraction, replacement, and a novel noising/denoising scheme that we introduce. Additional novel insights include: utilizing a data type taxonomy to both identify and obfuscate sensitive information and explicitly taking into account the utility of chat responses in making the obfuscation decision. First, we systematically optimize and evaluate each obfuscation action independently in terms of the privacy-utility tradeoff it achieves. Second, we propose PROMPTPET, an LLM-based agent that selects the best obfuscation action for each sensitive part of the prompt, using a reinforcement-learning inspired rule optimizer, applied for the first time in this context. Using a real-world chat dataset, we show that PROMPTPET matches the best privacy-utility tradeoff attainable by any single obfuscation action and significantly outperforms prior state-of-the-art approaches.

cs.CR↗

arXiv2026

Actions Speak Louder Than Chats: Investigating AI Chatbot Age Gating

AI chatbots are widely used by children and teens today, but they pose significant risks to youth's privacy and safety due to both increasingly personal conversations and potential exposure to unsafe content. While children under 13 are protected by the Children's Online Privacy Protection Act (COPPA), chatbot providers' own privacy policies may also provide protections, since they typically prohibit children from accessing their platforms. Age gating is often employed to restrict children online, but chatbot age gating in particular has not been studied. In this paper, we investigate whether popular consumer chatbots are (i) able to estimate users' ages based solely on their conversations, and (ii) whether they take action upon identifying children. To that end, we develop an auditing framework in which we programmatically interact with chatbots and conduct 1050 experiments using our comprehensive library of age-indicative prompts, including implicit and explicit age disclosures, to analyze the chatbots' responses and actions. We find that while chatbots are capable of estimating age, they do not take any action when children are identified, contradicting their own policies. Our methodology and findings provide insights for platform design, demonstrated by our proof-of-concept chatbot age gating implementation, and regulation to protect children online.

cs.HC↗

arXiv2026

VR ProfiLens: User Profiling Risks in Consumer Virtual Reality Apps

Virtual reality (VR) platforms and apps collect user sensor data, including motion, facial, eye, and hand data, in abstracted form. These data may expose users to unique privacy risks without their knowledge or meaningful awareness, yet the extent of these risks remains understudied. To address this gap, we propose VR ProfiLens, a framework to study user profiling based on VR sensor data and the resulting privacy risks across consumer VR apps. To systematically study this problem, we first develop a taxonomy rooted in the CCPA definition of personal information and expand it by sensor, app, and threat contexts to identify user attributes at risk. Then, we conduct a user study in which we collect VR sensor data from four sensor groups from real users interacting with 10 popular consumer VR apps, followed by a survey. We design and apply an analysis pipeline to demonstrate the feasibility of inferring user attributes using these data. Our results show that sensitive personal information can be inferred with moderately high to high risk (up to 90% F1 score) from abstracted sensor data. Through feature analysis, we further identify correlations among app groups and sensor groups in inferring user attributes. Our findings highlight risks to users, including privacy loss, tracking, targeted advertising, and safety threats. Finally, we discuss design implications and regulatory recommendations to enhance transparency and better protect users' privacy in VR.

cs.CR↗

arXiv2025

BLINDSPOT: Enabling Bystander-Controlled Privacy Signaling for Camera-Enabled Devices

Camera-equipped mobile devices, such as phones, smart glasses, and AR headsets, pose a privacy challenge for bystanders, who currently lack effective real-time mechanisms to control the capture of their picture, video, including their face. We present BlindSpot, an on-device system that enables bystanders to manage their own privacy by signaling their privacy preferences in real-time without previously sharing any sensitive information. Our main contribution is the design and comparative evaluation of three distinct signaling modalities: a hand gesture mechanism, a significantly improved visible light communication (VLC) protocol, and a novel ultra-wideband (UWB) communication protocol. For all these modalities, we also design a validation mechanism that uses geometric consistency checks to verify the origin of a signal relative to the sending bystander, and defend against impersonation attacks. We implement the complete system (BlindSpot) on a commodity smartphone and conduct a comprehensive evaluation of each modality's accuracy and latency across various distances, lighting conditions, and user movements. Our results demonstrate the feasibility of these novel bystander signaling techniques and their trade-offs in terms of system performance and convenience.

cs.CR↗

arXiv2025

When Kids Mode Isn't For Kids: Investigating TikTok's "Under 13 Experience"

TikTok, the social media platform that is popular among children and adolescents, offers a more restrictive "Under 13 Experience" exclusively for young users in the US, also known as TikTok's "Kids Mode". While prior research has studied various aspects of TikTok's regular mode, including privacy and personalization, TikTok's Kids Mode remains understudied, and there is a lack of transparency regarding its content curation and its safety and privacy protections for children. In this paper, (i) we propose an auditing methodology to comprehensively investigate TikTok's Kids Mode and (ii) we apply it to characterize the platform's content curation and determine the prevalence of child-directed content, based on regulations in the Children's Online Privacy Protection Act (COPPA). We find that 83% of videos observed on the "For You" page in Kids Mode are actually not child-directed, and even inappropriate content was found. The platform also lacks critical features, namely parental controls and accessibility settings. Our findings have important design and regulatory implications, as children may be incentivized to use TikTok's regular mode instead of Kids Mode, where they are known to be exposed to further safety and privacy risks.

cs.HC↗

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

AutoLike: Auditing Social Media Recommendations through User Interactions

Modern social media platforms, such as TikTok, Facebook, and YouTube, rely on recommendation systems to personalize content for users based on user interactions with endless streams of content, such as "For You" pages. However, these complex algorithms can inadvertently deliver problematic content related to self-harm, mental health, and eating disorders. We introduce AutoLike, a framework to audit recommendation systems in social media platforms for topics of interest and their sentiments. To automate the process, we formulate the problem as a reinforcement learning problem. AutoLike drives the recommendation system to serve a particular type of content through interactions (e.g., liking). We apply the AutoLike framework to the TikTok platform as a case study. We evaluate how well AutoLike identifies TikTok content automatically across nine topics of interest; and conduct eight experiments to demonstrate how well it drives TikTok's recommendation system towards particular topics and sentiments. AutoLike has the potential to assist regulators in auditing recommendation systems for problematic content. (Warning: This paper contains qualitative examples that may be viewed as offensive or harmful.)

cs.LG↗

arXiv2024

BehaVR: User Identification Based on VR Sensor Data

Virtual reality (VR) platforms enable a wide range of applications, however, pose unique privacy risks. In particular, VR devices are equipped with a rich set of sensors that collect personal and sensitive information (e.g., body motion, eye gaze, hand joints, and facial expression). The data from these newly available sensors can be used to uniquely identify a user, even in the absence of explicit identifiers. In this paper, we seek to understand the extent to which a user can be identified based solely on VR sensor data, within and across real-world apps from diverse genres. We consider adversaries with capabilities that range from observing APIs available within a single app (app adversary) to observing all or selected sensor measurements across multiple apps on the VR device (device adversary). To that end, we introduce BehaVR, a framework for collecting and analyzing data from all sensor groups collected by multiple apps running on a VR device. We use BehaVR to collect data from real users that interact with 20 popular real-world apps. We use that data to build machine learning models for user identification within and across apps, with features extracted from available sensor data. We show that these models can identify users with an accuracy of up to 100%, and we reveal the most important features and sensor groups, depending on the functionality of the app and the adversary. To the best of our knowledge, BehaVR is the first to analyze user identification in VR comprehensively, i.e., considering all sensor measurements available on consumer VR devices, collected by multiple real-world, as opposed to custom-made, apps.

cs.HC↗

arXiv2024

VBIT: Towards Enhancing Privacy Control Over IoT Devices

Internet-of-Things (IoT) devices are increasingly deployed at home, at work, and in other shared and public spaces. IoT devices collect and share data with service providers and third parties, which poses privacy concerns. Although privacy enhancing tools are quite advanced in other applications domains (\eg~ advertising and tracker blockers for browsers), users have currently no convenient way to know or manage what and how data is collected and shared by IoT devices. In this paper, we present VBIT, an interactive system combining Mixed Reality (MR) and web-based applications that allows users to: (1) uncover and visualize tracking services by IoT devices in an instrumented space and (2) take action to stop or limit that tracking. We design and implement VBIT to operate at the network traffic level, and we show that it has negligible performance overhead, and offers flexibility and good usability. We perform a mixed-method user study consisting of an online survey and an in-person interview study. We show that VBIT users appreciate VBIT's transparency, control, and customization features, and they become significantly more willing to install an IoT advertising and tracking blocker, after using VBIT. In the process, we obtain design insights that can be used to further iterate and improve the design of VBIT and other systems for IoT transparency and control.

cs.HC↗

arXiv2024

Understanding Privacy Norms through Web Forms

Web forms are one of the primary ways to collect personal information online, yet they are relatively under-studied. Unlike web tracking, data collection through web forms is explicit and contextualized. Users (i) are asked to input specific personal information types, and (ii) know the specific context (i.e., on which website and for what purpose). For web forms to be trusted by users, they must meet the common sense standards of appropriate data collection practices within a particular context (i.e., privacy norms). In this paper, we extract the privacy norms embedded within web forms through a measurement study. First, we build a specialized crawler to discover web forms on websites. We run it on 11,500 popular websites, and we create a dataset of 293K web forms. Second, to process data of this scale, we develop a cost-efficient way to annotate web forms with form types and personal information types, using text classifiers trained with assistance of large language models (LLMs). Third, by analyzing the annotated dataset, we reveal common patterns of data collection practices. We find that (i) these patterns are explained by functional necessities and legal obligations, thus reflecting privacy norms, and that (ii) deviations from the observed norms often signal unnecessary data collection. In addition, we analyze the privacy policies that accompany web forms. We show that, despite their wide adoption and use, there is a disconnect between privacy policy disclosures and the observed privacy norms.

cs.CR↗

arXiv2024

DiffAudit: Auditing Privacy Practices of Online Services for Children and Adolescents

Children's and adolescents' online data privacy are regulated by laws such as the Children's Online Privacy Protection Act (COPPA) and the California Consumer Privacy Act (CCPA). Online services that are directed towards general audiences (i.e., including children, adolescents, and adults) must comply with these laws. In this paper, first, we present DiffAudit, a platform-agnostic privacy auditing methodology for general audience services. DiffAudit performs differential analysis of network traffic data flows to compare data processing practices (i) between child, adolescent, and adult users and (ii) before and after consent is given and user age is disclosed. We also present a data type classification method that utilizes GPT-4 and our data type ontology based on COPPA and CCPA, allowing us to identify considerably more data types than prior work. Second, we apply DiffAudit to a set of popular general audience mobile and web services and observe a rich set of behaviors extracted from over 440K outgoing requests, containing 3,968 unique data types we extracted and classified. We reveal problematic data processing practices prior to consent and age disclosure, lack of differentiation between age-specific data flows, inconsistent privacy policy disclosures, and sharing of linkable data with third parties, including advertising and tracking services.

cs.CR↗

arXiv2024

Maverick-Aware Shapley Valuation for Client Selection in Federated Learning

Federated Learning (FL) allows clients to train a model collaboratively without sharing their private data. One key challenge in practical FL systems is data heterogeneity, particularly in handling clients with rare data, also referred to as Mavericks. These clients own one or more data classes exclusively, and the model performance becomes poor without their participation. Thus, utilizing Mavericks throughout training is crucial. In this paper, we first design a Maverick-aware Shapley valuation that fairly evaluates the contribution of Mavericks. The main idea is to compute the clients' Shapley values (SV) class-wise, i.e., per label. Next, we propose FedMS, a Maverick-Shapley client selection mechanism for FL that intelligently selects the clients that contribute the most in each round, by employing our Maverick-aware SV-based contribution score. We show that, compared to an extensive list of baselines, FedMS achieves better model performance and fairer Shapley Rewards distribution.

cs.LG↗

arXiv2024

Location Leakage in Federated Signal Maps

We consider the problem of predicting cellular network performance (signal maps) from measurements collected by several mobile devices. We formulate the problem within the online federated learning framework: (i) federated learning (FL) enables users to collaboratively train a model, while keeping their training data on their devices; (ii) measurements are collected as users move around over time and are used for local training in an online fashion. We consider an honest-but-curious server, who observes the updates from target users participating in FL and infers their location using a deep leakage from gradients (DLG) type of attack, originally developed to reconstruct training data of DNN image classifiers. We make the key observation that a DLG attack, applied to our setting, infers the average location of a batch of local data, and can thus be used to reconstruct the target users' trajectory at a coarse granularity. We build on this observation to protect location privacy, in our setting, by revisiting and designing mechanisms within the federated learning framework including: tuning the FL parameters for averaging, curating local batches so as to mislead the DLG attacker, and aggregating across multiple users with different trajectories. We evaluate the performance of our algorithms through both analysis and simulation based on real-world mobile datasets, and we show that they achieve a good privacy-utility tradeoff.

cs.LG↗

arXiv2023

Seqnature: Extracting Network Fingerprints from Packet Sequences

This paper proposes a general network fingerprinting framework, Seqnature, that uses packet sequences as its basic data unit and that makes it simple to implement any fingerprinting technique that can be formulated as a problem of identifying packet exchanges that consistently occur when the fingerprinted event is triggered. We demonstrate the versatility of Seqnature by using it to implement five different fingerprinting techniques, as special cases of the framework, which broadly fall into two categories: (i) fingerprinting techniques that consider features of each individual packet in a packet sequence, e.g., size and direction; and (ii) fingerprinting techniques that only consider stream-wide features, specifically what Internet endpoints are contacted. We illustrate how Seqnature facilitates comparisons of the relative performance of different fingerprinting techniques by applying the five fingerprinting techniques to datasets from the literature. The results confirm findings in prior work, for example that endpoint information alone is insufficient to differentiate between individual events on Internet of Things devices, but also show that smart TV app fingerprints based exclusively on endpoint information are not as distinct as previously reported.

cs.CR↗

arXiv2023

PriPrune: Quantifying and Preserving Privacy in Pruned Federated Learning

Federated learning (FL) is a paradigm that allows several client devices and a server to collaboratively train a global model, by exchanging only model updates, without the devices sharing their local training data. These devices are often constrained in terms of communication and computation resources, and can further benefit from model pruning -- a paradigm that is widely used to reduce the size and complexity of models. Intuitively, by making local models coarser, pruning is expected to also provide some protection against privacy attacks in the context of FL. However this protection has not been previously characterized, formally or experimentally, and it is unclear if it is sufficient against state-of-the-art attacks. In this paper, we perform the first investigation of privacy guarantees for model pruning in FL. We derive information-theoretic upper bounds on the amount of information leaked by pruned FL models. We complement and validate these theoretical findings, with comprehensive experiments that involve state-of-the-art privacy attacks, on several state-of-the-art FL pruning schemes, using benchmark datasets. This evaluation provides valuable insights into the choices and parameters that can affect the privacy protection provided by pruning. Based on these insights, we introduce PriPrune -- a privacy-aware algorithm for local model pruning, which uses a personalized per-client defense mask and adapts the defense pruning rate so as to jointly optimize privacy and model performance. PriPrune is universal in that can be applied after any pruned FL scheme on the client, without modification, and protects against any inversion attack by the server. Our empirical evaluation demonstrates that PriPrune significantly improves the privacy-accuracy tradeoff compared to state-of-the-art pruned FL schemes that do not take privacy into account.

cs.LG↗

arXiv2023

GaitGuard: Protecting Video-Based Gait Privacy in Mixed Reality

Mixed Reality (MR) systems capture continuous video streams that expose bystanders' and collaborators' gait patterns -- a biometric revealing sensitive attributes including age, gender, and health conditions. We show that video-based gait profiling achieves 78\% accuracy (15.6$\times$ random chance) on unprotected MR feeds, motivating \textbf{GaitGuard}, a real-time defense operating on a companion mobile device. GaitGuard introduces \textbf{GaitExtract}, an automated gait feature extraction pipeline adapted from clinical analysis for egocentric MR perspectives. Through systematic evaluation of 233 mitigation configurations, we characterize privacy-utility-performance trade-offs. A key insight is that gait features derive primarily from transient events (heel strikes, toe-offs). We exploit this temporal sparsity through adaptive mitigation that selectively processes only gait-critical frames, achieving a 68\% reduction in profiling accuracy while preserving visual quality (SSIM: 0.97) at 29~FPS. \textbf{GaitGuard} scales to 10 simultaneous users with under 10ms latency. A qualitative study of 20-participants confirms that the users preferred a solution such as \textbf{GaitGuard} which provides privacy guarantees.

cs.HC↗

arXiv2023

Tracking, Profiling, and Ad Targeting in the Alexa Echo Smart Speaker Ecosystem

Smart speakers collect voice commands, which can be used to infer sensitive information about users. Given the potential for privacy harms, there is a need for greater transparency and control over the data collected, used, and shared by smart speaker platforms as well as third party skills supported on them. To bridge this gap, we build a framework to measure data collection, usage, and sharing by the smart speaker platforms. We apply our framework to the Amazon smart speaker ecosystem. Our results show that Amazon and third parties, including advertising and tracking services that are unique to the smart speaker ecosystem, collect smart speaker interaction data. We also find that Amazon processes smart speaker interaction data to infer user interests and uses those inferences to serve targeted ads to users. Smart speaker interaction also leads to ad targeting and as much as 30X higher bids in ad auctions, from third party advertisers. Finally, we find that Amazon's and third party skills' data practices are often not clearly disclosed in their policy documents.

cs.CR↗

arXiv2023

A CI-based Auditing Framework for Data Collection Practices

Apps and devices (mobile devices, web browsers, IoT, VR, voice assistants, etc.) routinely collect user data, and send them to first- and third-party servers through the network. Recently, there is a lot of interest in (1) auditing the actual data collection practices of those systems; and also in (2) checking the consistency of those practices against the statements made in the corresponding privacy policies. In this paper, we argue that the contextual integrity (CI) tuple can be the basic building block for defining and implementing such an auditing framework. We elaborate on the special case where the tuple is partially extracted from the network traffic generated by the end-device of interest, and partially from the corresponding privacy policies using natural language processing (NLP) techniques. Along the way, we discuss related bodies of work and representative examples that fit into that framework. More generally, we believe that CI can be the building block not only for auditing at the edge, but also for specifying privacy policies and system APIs. We also discuss limitations and directions for future work.

cs.CR↗