211 results
Now showing1 - 10 of 211
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Atlas synchronization in the Hierarchical Federated Learning continuumIn Hierarchical Federated Learning (HFL), bandwidth budgets and delay constraints can prevent the timely synchronization of the semantic atlases (summaries) required for clients to learn unseen classes. Conventional synchronization policies typically optimize for geometric freshness. However, staleness becomes most harmful when it changes discrete curriculum gating decisions. We find that reducing feature space drift alone is an unreliable proxy for knowledge void recovery under constraints, because learning depends on decision consistency. Our Decision-Critical Atlas Synchronization (DCAS) policy prioritizes updates that are likely to alter these decisions and accelerates recovery from knowledge voids compared to a geometry-centric baseline.Publicationtype: Conference Paper13 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Cost-effective processing of IoT data in the computing continuumProcessing real-time data in the cloud has become the basis for various IoT applications. This processing typically incurs a high pricing cost, due to the use of paid messaging services (e.g., AWS SQS, or GCP Pub/Sub) that send real-time data from IoT devices at the edge to IoT applications in the cloud. Alternatively, costly AI-enabled IoT devices are employed for federated learning at the edge, which lowers the amount of data sent to the cloud. To reduce such costs, we propose an approach that sends real-time data from the IoT device to the cloud with reduced sampling frequency. In the cloud, we use AI to predict the missing data, and send both real and predicted data to the IoT application. This way, the IoT application receives the same amount of data, although less data is sent from the edge to the cloud (using messaging services). In addition, we measure the prediction error in the cloud, and adjust the sampling frequency at the edge, so that the error remains low. Thus, this approach lowers the cost of IoT applications by reducing the use of paid messaging services, and avoiding costly AI-enabled IoT devices, while also ensuring a low prediction error. For the evaluation, we build a prototype, and we experiment with real-world IoT data. Our experiments show promising results, including a reduction in costs by about 70% with a prediction error of around 5%.Publicationtype: Conference Paper17 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Routing cross-blockchain communicationBlockchain Interoperability Solutions (BISs) enable seamless communication and transactions between two or more blockchains. These solutions form an additional heterogeneous set on top of the blockchain layer and impose new constraints on cross-blockchain communication. This new interconnected network of blockchains can provide different communication routes, resulting in the need to find an optimal route between the source and target blockchains. In this paper, we aim to foster discussion about the problems and opportunities that the widescale adoption of BISs brings. We define the problem of using multiple BISs to route cross-blockchain communication and develop theoretical foundations for cross-blockchain routing. Based on the formalization, we implement and evaluate an algorithm that returns an optimal route for a communication request, given a network of blockchains and user-defined objectives.Publicationtype: Conference Paper42 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Securing blockchain-based distributed learning for heterogeneous clients through knowledge distillation and zero-knowledge proofsDistributed learning (DL) is gaining popularity as it enables clients (e.g., AI Agents) to enhance their machine learning (ML) models’ performance by exchanging knowledge without revealing private datasets. State-of-the-art DL approaches primarily focus on transferring knowledge between heterogeneous clients with diverse model architectures, connecting clients with those that can improve their models, and protecting data privacy. However, they overlook the threat of malicious clients that potentially downgrade the models’ performance by sharing inaccurate knowledge or excluding high-performing clients from the training procedure.Therefore, we introduce the Zero-Knowledge Blockchain-Based Knowledge Distillation Learning Framework (zkBKD). In zkBKD, heterogeneous clients communicate with a blockchain network to discover high-performing clients, verify zero-knowledge proofs (ZKPs) to ensure the correctness of the knowledge shared from other clients, and vote to eliminate malicious clients. We analyze security and privacy risks and show that zkBKD prevents membership, poisoning, and collusion attacks. We conduct extensive experiments on two standard datasets across heterogeneous clients with four model architectures. The experimental results demonstrate that zkBKD relatively improves the average model accuracy of all clients by 25.71%. Even lightweight models such as ResNet-2 achieve up to a 103.35% accuracy gain compared to independent training.Publicationtype: Conference Paper53 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , An AI-powered auto-completion tool for Solidity smart contractsSolidity smart contracts are widely used to implement decentralized applications. However, their development remains challenging due to the language’s domain-specific complexity, the immutability of deployed contracts, which prevents post-deployment fixes, and the high risk of introducing security-critical vulnerabilities. While Large Language Models (LLMs) have advanced code generation across general domains, they often struggle to meet the structural and security-specific demands of smart contract development. Therefore, this paper presents a domain-adapted code completion model trained on 22,000 labeled code constructs extracted from Solidity contracts. The model is built on a transformer-based architecture and fine-tuned using Quantized Low-Rank Adaptation (QLoRA), a parameter-efficient method. The dataset is processed to highlight secure coding patterns and structural semantics, enabling the model to learn from both preceding and succeeding contexts. Evaluation using perplexity, the Bilingual Evaluation Understudy (BLEU) score, and the Metric for Evaluation of Translation with Explicit Ordering (METEOR) shows significant improvements with consistent gains across all three metrics compared to the base model. These results demonstrate that targeted adaptation of language models can significantly enhance coding support in Solidity smart contracts.Publicationtype: Conference Paper36 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , UPPR: universal privacy-preserving revocation(IEEE, 2025-10); ; ; ; Self-Sovereign Identity (SSI) frameworks enable individuals to receive and present digital credentials in a user-controlled way. Revocation mechanisms ensure that invalid or withdrawn credentials cannot be misused. These revocation mechanisms must be scalable (e.g., at national scale) and preserve core SSI principles such as privacy, user control, and interoperability. Achieving both is hard, and finding a suitable trade-off remains a key challenge in SSI research.This paper introduces UPPR, a revocation mechanism for One-Show Verifiable Credentials (oVCs) and unlinkable Anonymous Credentials (ACs). Revocations are managed using percredential Verifiable Random Function (VRF) tokens, which are published in a Bloom filter cascade on a blockchain. Holders prove non-revocation via a VRF proof for oVCs or a single Zero-Knowledge Proof for ACs. The construction prevents revocation status tracking, allows holders to stay offline, and hides issuer revocation behavior. We analyze the privacy properties of UPPR and provide a prototype implementation on Ethereum. Our implementation enables off-chain verification at no cost. On-chain checks cost 0.56–0.84 USD, while issuers pay only 0.00002–0.00005 USD per credential to refresh the revocation state.Publicationtype: Conference Paper43 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Detect, adapt, overcome: mitigating concept drift in federated learningFederated Learning (FL) is a distributed machine learning paradigm where a central server coordinates the training of a global model across multiple decentralized clients. Most FL algorithms assume stationary data-generating processes and neglect concept drift, i.e., the change of data distributions over time. This results in a gradual decline of the model's performance and eventually renders the model obsolete. We investigate the impact of concept drift in FL and propose an active approach to detect and adapt to drift. Our detection method is based on local model loss which allows us to categorize clients based on the type of drift they experience and apply appropriate adaptive measures. Through extensive experiments, we demonstrate the efficiency, accuracy, and precision of our approach: the proposed adaptation approach successfully accelerates convergence for drifted clients, outperforming the baseline algorithm. Even under extreme drift conditions, our global model remains stable. This demonstrates the superior robustness of our approach compared to conventional methods.Publicationtype: Conference Paper61 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , FLUID: federated learning with unlearning and instant drift-recoveryFederated Learning (FL) enables collaborative model training without sharing raw data, but struggles with concept drift, where client data distributions evolve over time. Existing approaches either retain outdated knowledge or suffer from high computational costs due to frequent retraining. This work introduces Federated Learning with Unlearning and Instant Driftrecovery (FLUID), a novel framework that treats concept drift as a selective forgetting problem. By leveraging techniques from Federated Unlearning, FLUID removes obsolete knowledge while adapting to new data patterns. It combines the lightweight unlearning capability of Federated Auxiliary Unlearning (FedAU) with the rapid recovery capability of Rapid Retraining (RRT), without requiring full retraining. Experimental results show that FLUID achieves balanced, all-around performance matching RRT in recovery speed and better convergence, and FedAU in lower accuracy dips during drift, and it outperforms natural recovery capabilities of Federated Averaging (FedAvg), and retraining from scratch.Publicationtype: Conference Paper81 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Transactional cross-chain smart contract invocations(Association for Computing Machinery (ACM), 2025-06-13); ; ; ; Blockchains have become increasingly important in recent years and have expanded their applicability to many domains beyond finance and cryptocurrencies. This adoption has particularly increased with the introduction of smart contracts, which are immutable, user-defined programs directly deployed on blockchain networks. However, many scenarios require business transactions to simultaneously access smart contracts on multiple, possibly heterogeneous blockchain networks while ensuring the atomicity and isolation of these transactions, which is not natively supported by current blockchain systems. Therefore, in this work, we introduce the Transactional Cross-Chain Smart Contract Invocation (TCCSCI) approach that supports such distributed business transactions while ensuring their global atomicity and serializability. The approach introduces the concept of Resource Manager Smart Contracts, and 2PC for Blockchains (2PC4BC), a client-driven Atomic Commit Protocol (ACP) specialized for blockchain-based distributed transactions. We validate our approach using a prototypical implementation, evaluate its introduced overhead, and prove its correctness.Publicationtype: Journal Article55 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Hierarchical bidirectional aggregation for federated learning under concept driftFederated Learning (FL) enables collaborative model training across decentralized clients while preserving data privacy. However, real-world FL deployments face two fundamental challenges: heterogeneous data distributions and concept drift, where data distributions evolve over time. While traditional FL assumes a star topology, real-world scenarios often employ hierarchical federated learning based on tree topologies that improve scalability and communication efficiency. In this paper, we introduce Hierarchical Bidirectional Averaging (HBA), a novel aggregation strategy for hierarchical federated networks designed to enhance resilience against data heterogeneity and concept drift. Our main result is that HBA significantly strengthens the resilience of FL against concept drift. In particular, our key findings demonstrate that (1) servers higher in the hierarchy exhibit greater accuracy stability and retain generalized model representations while the lower servers capture more localized and fine-grained details, (2) increasing tree height improves overall client accuracy, and (3) our aggregation strategy enhances generalization and facilitates a balanced information flow across the hierarchy, resulting in faster recovery from concept drift.Publicationtype: Conference Paper39