2 citations · 7 across the 28 of their papers we have counts for
29 papers
Checking Leakage Witnesses versus Certifying Bounded Non-Leakage
Chao Feng, Burkhard Stiller
When a language-model audit finds no leak, what is needed to certify non-leakage? We study guarantees over a declared prompt domain under an executable leakage criterion and decodi…
CACTUS: Mask-Guided Semantic Clean-Label Backdoors in Decentralized Federated Learning
Chao Feng, Burkhard Stiller
Semantic triggers in federated learning (FL) can be less conspicuous than synthetic patches, but sample-dependent placement may weaken backdoor implantation across aggregation roun…
UnlinkableDFL: A Framework for Network-Layer Unlinkability in Decentralized Federated Learning
Chao Feng, Thomas Grubl, Jan von der Assen +4
Decentralized Federated Learning (DFL) removes the central aggregator of conventional Federated Learning, but peer-to-peer model exchange still exposes network traces: who communic…
Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive HIL Testing
Chao Feng, Zihan Liu, Siddhant Gupta +3
Hardware-in-the-Loop (HIL) testing is essential for automotive validation but suffers from fragmented and underutilized test artifacts. This paper presents HIL-GPT, a retrieval-aug…
Bridging Technical Capability and User Accessibility: Off-grid Civilian Emergency Communication
Karim Khamaisi, Oliver Kamer, Bruno Rodrigues +2
During large-scale crises disrupting cellular and Internet infrastructure, civilians lack reliable methods for communication, aid coordination, and access to trustworthy informatio…
FEST: A Unified Framework for Evaluating Synthetic Tabular Data
Weijie Niu, Alberto Huertas Celdran, Karoline Siarsky +1
Synthetic data generation, leveraging generative machine learning techniques, offers a promising approach to mitigating privacy concerns associated with real-world data usage. Synt…
A Crowdsensing Intrusion Detection Dataset For Decentralized Federated Learning Models
Chao Feng, Alberto Huertas Celdran, Jing Han +6
This paper introduces a dataset and an experimental study on Decentralized Federated Learning (DFL) for Internet of Things (IoT) crowdsensing malware detection. The dataset compris…
Demo: A Practical Testbed for Decentralized Federated Learning on Physical Edge Devices
Chao Feng, Nicolas Huber, Alberto Huertas Celdran +2
Federated Learning (FL) enables collaborative model training without sharing raw data, preserving participant privacy. Decentralized FL (DFL) eliminates reliance on a central serve…
AugMixCloak: A Defense against Membership Inference Attacks via Image Transformation
Heqing Ren, Chao Feng, Alberto Huertas +1
Traditional machine learning (ML) raises serious privacy concerns, while federated learning (FL) mitigates the risk of data leakage by keeping data on local devices. However, the t…
QUIC-Exfil: Exploiting QUIC's Server Preferred Address Feature to Perform Data Exfiltration Attacks
Thomas Grübl, Weijie Niu, Jan von der Assen +1
The QUIC protocol is now widely adopted by major tech companies and accounts for a significant fraction of today's Internet traffic. QUIC's multiplexing capabilities, encrypted hea…
DMPA: Model Poisoning Attacks on Decentralized Federated Learning for Model Differences
Chao Feng, Yunlong Li, Yuanzhe Gao +4
Federated learning (FL) has garnered significant attention as a prominent privacy-preserving Machine Learning (ML) paradigm. Decentralized FL (DFL) eschews traditional FL's central…
GreenDFL: a Framework for Assessing the Sustainability of Decentralized Federated Learning Systems
Chao Feng, Alberto Huertas Celdrán, Xi Cheng +2
Decentralized Federated Learning (DFL) is an emerging paradigm that enables collaborative model training without centralized data and model aggregation, enhancing privacy and resil…
ColNet: Collaborative Optimization in Decentralized Federated Multi-task Learning Systems
Chao Feng, Nicolas Fazli Kohler, Zhi Wang +4
The integration of Federated Learning (FL) and Multi-Task Learning (MTL) has been explored to address client heterogeneity, with Federated Multi-Task Learning (FMTL) treating each…
From Models to Network Topologies: A Topology Inference Attack in Decentralized Federated Learning
Chao Feng, Yuanzhe Gao, Alberto Huertas Celdran +2
Federated Learning (FL) is widely recognized as a privacy-preserving Machine Learning paradigm due to its model-sharing mechanism that avoids direct data exchange. Nevertheless, mo…
FedEP: Tailoring Attention to Heterogeneous Data Distribution with Entropy Pooling for Decentralized Federated Learning
Chao Feng, Hongjie Guan, Alberto Huertas Celdrán +3
Non-Independent and Identically Distributed (non-IID) data in Federated Learning (FL) causes client drift issues, leading to slower convergence and reduced model performance. While…
De-VertiFL: A Solution for Decentralized Vertical Federated Learning
Alberto Huertas Celdrán, Chao Feng, Sabyasachi Banik +3
Federated Learning (FL), introduced in 2016, was designed to enhance data privacy in collaborative model training environments. Among the FL paradigm, horizontal FL, where clients…
Leveraging MTD to Mitigate Poisoning Attacks in Decentralized FL with Non-IID Data
Chao Feng, Alberto Huertas Celdrán, Zien Zeng +4
Decentralized Federated Learning (DFL), a paradigm for managing big data in a privacy-preserved manner, is still vulnerable to poisoning attacks where malicious clients tamper with…
Towards Threat Modelling of IoT Context-Sharing Platforms
Mohammad Goudarzi, Arash Shaghaghi, Simon Finn +2
The Internet of Things (IoT) involves complex, interconnected systems and devices that depend on context-sharing platforms for interoperability and information exchange. These plat…
PACCOR4ESP: Embedded Device Security Attestation using Platform Attribute Certificates
Thomas Grübl, Jan von der Assen, Markus Knecht +1
Verifying the integrity of embedded device characteristics is required to ensure secure operation of a device. One central challenge is to securely extract and store device-specifi…
DART: A Solution for Decentralized Federated Learning Model Robustness Analysis
Chao Feng, Alberto Huertas Celdrán, Jan von der Assen +3
Federated Learning (FL) has emerged as a promising approach to address privacy concerns inherent in Machine Learning (ML) practices. However, conventional FL methods, particularly…
The Danger Within: Insider Threat Modeling Using Business Process Models
Jan von der Assen, Jasmin Hochuli, Thomas Grübl +1
Threat modeling has been successfully applied to model technical threats within information systems. However, a lack of methods focusing on non-technical assets and their represent…
Performance Analysis of Decentralized Physical Infrastructure Networks and Centralized Clouds
Jan von der Assen, Christian Killer, Alessandro De Carli +1
The advent of Decentralized Physical Infrastructure Networks (DePIN) represents a shift in the digital infrastructure of today's Internet. While Centralized Service Providers (CSP)…
Asset-centric Threat Modeling for AI-based Systems
Jan von der Assen, Jamo Sharif, Chao Feng +3
Threat modeling is a popular method to securely develop systems by achieving awareness of potential areas of future damage caused by adversaries. However, threat modeling for syste…
QuantTM: Business-Centric Threat Quantification for Risk Management and Cyber Resilience
Jan von der Assen, Muriel F. Franco, Muyao Dong +1
Threat modeling has emerged as a key process for understanding relevant threats within businesses. However, understanding the importance of threat events is rarely driven by the bu…