arXiv subjects

Kleomenis Katevas

Publications and source records attributed to Kleomenis Katevas.

At least 19 recordsLinked to original sources

arXiv2026

AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices

Autonomous agents powered by large language models (LLMs) are increasingly used to automate complex, multi-step tasks such as coding or web-based question answering. While remote, cloud-based agents offer scalability and ease of deployment, they raise privacy concerns, depend on network connectivity, and incur recurring API costs. Deploying agents locally on user devices mitigates these issues by preserving data privacy and eliminating usage-based fees. However, agentic workflows are far more resource-intensive than typical LLM interactions. Iterative reasoning, tool use, and failure retries substantially increase token consumption, often expending significant compute without successfully completing tasks. In this work, we investigate the time, token, and energy overhead of locally deployed LLM-based agents on consumer hardware. Our measurements show that agentic execution increases GPU power draw, temperature, and battery drain compared to single-inference workloads. To address this inefficiency, we introduce AgentStop, a lightweight efficiency supervisor that predicts and preemptively terminates trajectories unlikely to succeed. Leveraging low-cost execution signals, such as token-level log probabilities, AgentStop can reduce wasted energy by 15-20% with minimal impact on task performance (<5% utility drop) for challenging web-based question answering and coding benchmarks. These findings position predictive early termination as a practical mechanism for enabling sustainable, privacy-preserving LLM agents on user devices. Our project code and data are available at https://github.com/brave-experiments/AgentStop.

cs.LG↗

arXiv2024

Context-Aware Membership Inference Attacks against Pre-trained Large Language Models

Membership Inference Attacks (MIAs) on pre-trained Large Language Models (LLMs) aim at determining if a data point was part of the model's training set. Prior MIAs that are built for classification models fail at LLMs, due to ignoring the generative nature of LLMs across token sequences. In this paper, we present a novel attack on pre-trained LLMs that adapts MIA statistical tests to the perplexity dynamics of subsequences within a data point. Our method significantly outperforms prior approaches, revealing context-dependent memorization patterns in pre-trained LLMs.

cs.CL↗

arXiv2024

MELTing point: Mobile Evaluation of Language Transformers

Transformers have revolutionized the machine learning landscape, gradually making their way into everyday tasks and equipping our computers with "sparks of intelligence". However, their runtime requirements have prevented them from being broadly deployed on mobile. As personal devices become increasingly powerful and prompt privacy becomes an ever more pressing issue, we explore the current state of mobile execution of Large Language Models (LLMs). To achieve this, we have created our own automation infrastructure, MELT, which supports the headless execution and benchmarking of LLMs on device, supporting different models, devices and frameworks, including Android, iOS and Nvidia Jetson devices. We evaluate popular instruction fine-tuned LLMs and leverage different frameworks to measure their end-to-end and granular performance, tracing their memory and energy requirements along the way. Our analysis is the first systematic study of on-device LLM execution, quantifying performance, energy efficiency and accuracy across various state-of-the-art models and showcases the state of on-device intelligence in the era of hyperscale models. Results highlight the performance heterogeneity across targets and corroborates that LLM inference is largely memory-bound. Quantization drastically reduces memory requirements and renders execution viable, but at a non-negligible accuracy cost. Drawing from its energy footprint and thermal behavior, the continuous execution of LLMs remains elusive, as both factors negatively affect user experience. Last, our experience shows that the ecosystem is still in its infancy, and algorithmic as well as hardware breakthroughs can significantly shift the execution cost. We expect NPU acceleration, and framework-hardware co-design to be the biggest bet towards efficient standalone execution, with the alternative of offloading tailored towards edge deployments.

cs.LG↗

arXiv2023

P4L: Privacy Preserving Peer-to-Peer Learning for Infrastructureless Setups

Distributed (or Federated) learning enables users to train machine learning models on their very own devices, while they share only the gradients of their models usually in a differentially private way (utility loss). Although such a strategy provides better privacy guarantees than the traditional centralized approach, it requires users to blindly trust a centralized infrastructure that may also become a bottleneck with the increasing number of users. In this paper, we design and implement P4L: a privacy preserving peer-to-peer learning system for users to participate in an asynchronous, collaborative learning scheme without requiring any sort of infrastructure or relying on differential privacy. Our design uses strong cryptographic primitives to preserve both the confidentiality and utility of the shared gradients, a set of peer-to-peer mechanisms for fault tolerance and user churn, proximity and cross device communications. Extensive simulations under different network settings and ML scenarios for three real-life datasets show that P4L provides competitive performance to baselines, while it is resilient to different poisoning attacks. We implement P4L and experimental results show that the performance overhead and power consumption is minimal (less than 3mAh of discharge).

cs.LG↗

arXiv2022

FLaaS: Cross-App On-device Federated Learning in Mobile Environments

Federated Learning (FL) has recently emerged as a popular solution to distributedly train a model on user devices improving user privacy and system scalability. Major Internet companies have deployed FL in their applications for specific use cases (e.g., keyboard prediction or acoustic keyword trigger), and the research community has devoted significant attention to improving different aspects of FL (e.g., accuracy, privacy, efficiency). However, there is still a lack of a practical system to enable easy collaborative cross-silo FL training, in the context of mobile environments. In this work, we bridge this gap and propose FLaME, an end-to-end system (i.e., client-side framework and libraries, and central server) to enable intra- and inter-app training on mobile devices with different types of IID and NonIID data distributions, in a secure and easy to deploy fashion. Our design solves major technical challenges such as on-device training, secure and private single and cross-app model training, while being offered in an "as a service" model. We implement FLaME for Android devices and experimentally evaluate its performance in-lab and in-wild, on more than 140 users for over a month. Our results show the feasibility and benefits of the design in a realistic mobile context and provide several insights to the FL community on the practicality and usage of FL in the wild.

cs.CR↗

arXiv2022

BatteryLab: A Collaborative Platform for Power Monitoring

Advances in cloud computing have simplified the way that both software development and testing are performed. This is not true for battery testing for which state of the art test-beds simply consist of one phone attached to a power meter. These test-beds have limited resources, access, and are overall hard to maintain; for these reasons, they often sit idle with no experiment to run. In this paper, we propose to share existing battery testbeds and transform them into vantage points of BatteryLab, a power monitoring platform offering heterogeneous devices and testing conditions. We have achieved this vision with a combination of hardware and software which allow to augment existing battery test-beds with remote capabilities. BatteryLab currently counts three vantage points, one in Europe and two in the US, hosting three Android devices and one iPhone 7. We benchmark BatteryLab with respect to the accuracy of its battery readings, system performance, and platform heterogeneity. Next, we demonstrate how measurements can be run atop of BatteryLab by developing the "Web Power Monitor" (WPM), a tool which can measure website power consumption at scale. We released WPM and used it to report on the energy consumption of Alexa's top 1,000 websites across 3 locations and 4 devices (both Android and iOS).

cs.NI↗

arXiv2021

Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning

Since the inception of Recommender Systems (RS), the accuracy of the recommendations in terms of relevance has been the golden criterion for evaluating the quality of RS algorithms. However, by focusing on item relevance, one pays a significant price in terms of other important metrics: users get stuck in a "filter bubble" and their array of options is significantly reduced, hence degrading the quality of the user experience and leading to churn. Recommendation, and in particular session-based/sequential recommendation, is a complex task with multiple - and often conflicting objectives - that existing state-of-the-art approaches fail to address. In this work, we take on the aforementioned challenge and introduce Scalarized Multi-Objective Reinforcement Learning (SMORL) for the RS setting, a novel Reinforcement Learning (RL) framework that can effectively address multi-objective recommendation tasks. The proposed SMORL agent augments standard recommendation models with additional RL layers that enforce it to simultaneously satisfy three principal objectives: accuracy, diversity, and novelty of recommendations. We integrate this framework with four state-of-the-art session-based recommendation models and compare it with a single-objective RL agent that only focuses on accuracy. Our experimental results on two real-world datasets reveal a substantial increase in aggregate diversity, a moderate increase in accuracy, reduced repetitiveness of recommendations, and demonstrate the importance of reinforcing diversity and novelty as complementary objectives.

cs.LG↗

arXiv2021

PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments

We propose and implement a Privacy-preserving Federated Learning ($PPFL$) framework for mobile systems to limit privacy leakages in federated learning. Leveraging the widespread presence of Trusted Execution Environments (TEEs) in high-end and mobile devices, we utilize TEEs on clients for local training, and on servers for secure aggregation, so that model/gradient updates are hidden from adversaries. Challenged by the limited memory size of current TEEs, we leverage greedy layer-wise training to train each model's layer inside the trusted area until its convergence. The performance evaluation of our implementation shows that $PPFL$ can significantly improve privacy while incurring small system overheads at the client-side. In particular, $PPFL$ can successfully defend the trained model against data reconstruction, property inference, and membership inference attacks. Furthermore, it can achieve comparable model utility with fewer communication rounds (0.54$\times$) and a similar amount of network traffic (1.002$\times$) compared to the standard federated learning of a complete model. This is achieved while only introducing up to ~15% CPU time, ~18% memory usage, and ~21% energy consumption overhead in $PPFL$'s client-side.

cs.CR↗

arXiv2020

FLaaS: Federated Learning as a Service

Federated Learning (FL) is emerging as a promising technology to build machine learning models in a decentralized, privacy-preserving fashion. Indeed, FL enables local training on user devices, avoiding user data to be transferred to centralized servers, and can be enhanced with differential privacy mechanisms. Although FL has been recently deployed in real systems, the possibility of collaborative modeling across different 3rd-party applications has not yet been explored. In this paper, we tackle this problem and present Federated Learning as a Service (FLaaS), a system enabling different scenarios of 3rd-party application collaborative model building and addressing the consequent challenges of permission and privacy management, usability, and hierarchical model training. FLaaS can be deployed in different operational environments. As a proof of concept, we implement it on a mobile phone setting and discuss practical implications of results on simulated and real devices with respect to on-device training CPU cost, memory footprint and power consumed per FL model round. Therefore, we demonstrate FLaaS's feasibility in building unique or joint FL models across applications for image object detection in a few hours, across 100 devices.

cs.LG↗

arXiv2020

DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments

We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones and consumer IoT devices) are equipped with pre-trained DNNs for a variety of applications. This trend comes with privacy risks as models can leak information about their training data through effective membership inference attacks (MIAs). We evaluate the performance of DarkneTZ, including CPU execution time, memory usage, and accurate power consumption, using two small and six large image classification models. Due to the limited memory of the edge device's TEE, we partition model layers into more sensitive layers (to be executed inside the device TEE), and a set of layers to be executed in the untrusted part of the operating system. Our results show that even if a single layer is hidden, we can provide reliable model privacy and defend against state of the art MIAs, with only 3% performance overhead. When fully utilizing the TEE, DarkneTZ provides model protections with up to 10% overhead.

cs.LG↗

arXiv2020

Policy-Based Federated Learning

In this paper we present PoliFL, a decentralized, edge-based framework that supports heterogeneous privacy policies for federated learning. We evaluate our system on three use cases that train models with sensitive user data collected by mobile phones - predictive text, image classification, and notification engagement prediction - on a Raspberry Pi edge device. We find that PoliFL is able to perform accurate model training and inference within reasonable resource and time budgets while also enforcing heterogeneous privacy policies.

cs.CR↗

arXiv2019

BatteryLab, A Distributed Power Monitoring Platform For Mobile Devices

Recent advances in cloud computing have simplified the way that both software development and testing are performed. Unfortunately, this is not true for battery testing for which state of the art test-beds simply consist of one phone attached to a power meter. These test-beds have limited resources, access, and are overall hard to maintain; for these reasons, they often sit idle with no experiment to run. In this paper, we propose to share existing battery testing setups and build BatteryLab, a distributed platform for battery measurements. Our vision is to transform independent battery testing setups into vantage points of a planetary-scale measurement platform offering heterogeneous devices and testing conditions. In the paper, we design and deploy a combination of hardware and software solutions to enable BatteryLab's vision. We then preliminarily evaluate BatteryLab's accuracy of battery reporting, along with some system benchmarking. We also demonstrate how BatteryLab can be used by researchers to investigate a simple research question.

cs.DC↗

arXiv2019

Towards Characterizing and Limiting Information Exposure in DNN Layers

Pre-trained Deep Neural Network (DNN) models are increasingly used in smartphones and other user devices to enable prediction services, leading to potential disclosures of (sensitive) information from training data captured inside these models. Based on the concept of generalization error, we propose a framework to measure the amount of sensitive information memorized in each layer of a DNN. Our results show that, when considered individually, the last layers encode a larger amount of information from the training data compared to the first layers. We find that, while the neuron of convolutional layers can expose more (sensitive) information than that of fully connected layers, the same DNN architecture trained with different datasets has similar exposure per layer. We evaluate an architecture to protect the most sensitive layers within the memory limits of Trusted Execution Environment (TEE) against potential white-box membership inference attacks without the significant computational overhead.

cs.CR↗

arXiv2018

Finding Dory in the Crowd: Detecting Social Interactions using Multi-Modal Mobile Sensing

Remembering our day-to-day social interactions is challenging even if you aren't a blue memory challenged fish. The ability to automatically detect and remember these types of interactions is not only beneficial for individuals interested in their behavior in crowded situations, but also of interest to those who analyze crowd behavior. Currently, detecting social interactions is often performed using a variety of methods including ethnographic studies, computer vision techniques and manual annotation-based data analysis. However, mobile phones offer easier means for data collection that is easy to analyze and can preserve the user's privacy. In this work, we present a system for detecting stationary social interactions inside crowds, leveraging multi-modal mobile sensing data such as Bluetooth Smart (BLE), accelerometer and gyroscope. To inform the development of such system, we conducted a study with 24 participants, where we asked them to socialize with each other for 45 minutes. We built a machine learning system based on gradient-boosted trees that predicts both 1:1 and group interactions with 77.8% precision and 86.5% recall, a 30.2% performance increase compared to a proximity-based approach. By utilizing a community detection-based method, we further detected the various group formation that exist within the crowd. Using mobile phone sensors already carried by the majority of people in a crowd makes our approach particularly well suited to real-life analysis of crowd behavior and influence strategies.

cs.HC↗

arXiv2018

Typical Phone Use Habits: Intense Use Does Not Predict Negative Well-Being

Not all smartphone owners use their device in the same way. In this work, we uncover broad, latent patterns of mobile phone use behavior. We conducted a study where, via a dedicated logging app, we collected daily mobile phone activity data from a sample of 340 participants for a period of four weeks. Through an unsupervised learning approach and a methodologically rigorous analysis, we reveal five generic phone use profiles which describe at least 10% of the participants each: limited use, business use, power use, and personality- & externally induced problematic use. We provide evidence that intense mobile phone use alone does not predict negative well-being. Instead, our approach automatically revealed two groups with tendencies for lower well-being, which are characterized by nightly phone use sessions.

cs.HC↗

arXiv2018

Deep Private-Feature Extraction

We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model which is trained and evaluated based on information theoretic constraints. Using the selective exchange of information between a user's device and a service provider, DPFE enables the user to prevent certain sensitive information from being shared with a service provider, while allowing them to extract approved information using their model. We introduce and utilize the log-rank privacy, a novel measure to assess the effectiveness of DPFE in removing sensitive information and compare different models based on their accuracy-privacy tradeoff. We then implement and evaluate the performance of DPFE on smartphones to understand its complexity, resource demands, and efficiency tradeoffs. Our results on benchmark image datasets demonstrate that under moderate resource utilization, DPFE can achieve high accuracy for primary tasks while preserving the privacy of sensitive features.

stat.ML↗

arXiv2017

Continual Prediction of Notification Attendance with Classical and Deep Network Approaches

We investigate to what extent mobile use patterns can predict -- at the moment it is posted -- whether a notification will be clicked within the next 10 minutes. We use a data set containing the detailed mobile phone usage logs of 279 users, who over the course of 5 weeks received 446,268 notifications from a variety of apps. Besides using classical gradient-boosted trees, we demonstrate how to make continual predictions using a recurrent neural network (RNN). The two approaches achieve a similar AUC of ca. 0.7 on unseen users, with a possible operation point of 50% sensitivity and 80% specificity considering all notification types (an increase of 40% with respect to a probabilistic baseline). These results enable automatic, intelligent handling of mobile phone notifications without the need for user feedback or personalization. Furthermore, they showcase how forego feature-extraction by using RNNs for continual predictions directly on mobile usage logs. To the best of our knowledge, this is the first work that leverages mobile sensor data for continual, context-aware predictions of interruptibility using deep neural networks.

cs.HC↗

arXiv2017

Privacy-Preserving Deep Inference for Rich User Data on The Cloud

Deep neural networks are increasingly being used in a variety of machine learning applications applied to rich user data on the cloud. However, this approach introduces a number of privacy and efficiency challenges, as the cloud operator can perform secondary inferences on the available data. Recently, advances in edge processing have paved the way for more efficient, and private, data processing at the source for simple tasks and lighter models, though they remain a challenge for larger, and more complicated models. In this paper, we present a hybrid approach for breaking down large, complex deep models for cooperative, privacy-preserving analytics. We do this by breaking down the popular deep architectures and fine-tune them in a particular way. We then evaluate the privacy benefits of this approach based on the information exposed to the cloud service. We also asses the local inference cost of different layers on a modern handset for mobile applications. Our evaluations show that by using certain kind of fine-tuning and embedding techniques and at a small processing costs, we can greatly reduce the level of information available to unintended tasks applied to the data feature on the cloud, and hence achieving the desired tradeoff between privacy and performance.

cs.CV↗