139 citations · 174 across the 14 of their papers we have counts for
19 papers
Is Weight Tying Still Beneficial for Decoder-Only LLMs in Private Settings Under DP-SGD?
Razan El Mais, Ali Chehab, Ibrahim Issa +1
Differentially Private Stochastic Gradient Descent (DP-SGD) is a leading approach for privacy-preserving fine-tuning of large language models (LLMs). Many decoder-only LLMs employ…
Where to Defend? Layer-Wise Adversarial Training for Robust Transformer-Based Semantic Communications
Maria Slim, Razane Tajeddine, Mariette Awad +1
Deep learning-based semantic communication (DeepSC), a Transformer-based encoder-decoder, achieves semantic fidelity over noisy channels but remains vulnerable to adversarial pertu…
Algebraic Geometry Codes Approach the Half-Singleton Bound with Constant Field Size
Neehar Verma, Camilla Hollanti, Razane Tajeddine
We study linear codes for insertion and deletion (insdel) errors through the lens of evaluation codes. We develop a general framework for analyzing random puncturings of evaluation…
SignDeepSC: A Semantic Signature-based Approach for Robust Semantic Communication
Khalil Alhaj, Razane Tajeddine, Hadi Sarieddeen
Semantic communication systems such as deep semantic communication (DeepSC) offer high efficiency but are vulnerable to adversarial attacks on their underlying neural networks. We…
Benchmarking Dataset for Presence-Only Passive Reconnaissance in Wireless Smart-Grid Communications
Bochra Al Agha, Razane Tajeddine
Benchmarking presence-only passive reconnaissance in smart-grid communications is challenging because the adversary is receive-only, yet nearby observers can still alter propagatio…
On the Extension of Private Distributed Matrix Multiplication Schemes to the Grid Partition
Christoph Hofmeister, Razane Tajeddine, Antonia Wachter-Zeh +1
We consider polynomial codes for private distributed matrix multiplication (PDMM/SDMM). Existing codes for PDMM are either specialized for the outer product partitioning (OPP), or…
On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models
Ali Al Sahili, Ali Chehab, Razane Tajeddine
Large Language Models (LLMs) are prone to memorizing training data, which poses serious privacy risks. Two of the most prominent concerns are training data extraction and Membershi…
Federated Spatiotemporal Graph Learning for Passive Attack Detection in Smart Grids
Bochra Al Agha, Razane Tajeddine
Smart grids are exposed to passive eavesdropping, where attackers listen silently to communication links. Although no data is actively altered, such reconnaissance can reveal grid…
Can Small-Scale Data Poisoning Exacerbate Dialect-Linked Biases in Large Language Models?
Chaymaa Abbas, Mariette Awad, Razane Tajeddine
Style-conditioned data poisoning is identified as a covert vector for amplifying sociolinguistic bias in large language models. Using small poisoned budgets that pair dialectal pro…
Mitigating Disparate Impact of Differentially Private Learning through Bounded Adaptive Clipping
Linzh Zhao, Aki Rehn, Mikko A. Heikkilä +2
Differential privacy (DP) has become an essential framework for privacy-preserving machine learning. Existing DP learning methods, however, often have disparate impacts on model pr…
Modular Polynomial Codes for Secure and Robust Distributed Matrix Multiplication
David Karpuk, Razane Tajeddine
We present Modular Polynomial (MP) Codes for Secure Distributed Matrix Multiplication (SDMM). The construction is based on the observation that one can decode certain proper subset…
Privacy-preserving Data Sharing on Vertically Partitioned Data
Razane Tajeddine, Joonas Jälkö, Samuel Kaski +1
In this work, we introduce a differentially private method for generating synthetic data from vertically partitioned data, \emph{i.e.}, where data of the same individuals is distri…
Private Information Retrieval Schemes with Regenerating Codes
Julien Lavauzelle, Razane Tajeddine, Ragnar Freij-Hollanti +1
A private information retrieval (PIR) scheme allows a user to retrieve a file from a database without revealing any information on the file being requested. As of now, PIR schemes…
Private Information Retrieval over Random Linear Networks
Razane Tajeddine, Antonia Wachter-Zeh, Camilla Hollanti
In this paper, the problem of providing privacy to users requesting data over a network from a distributed storage system (DSS) is considered. The DSS, which is considered as the m…
Private Information Retrieval from Coded Storage Systems with Colluding, Byzantine, and Unresponsive Servers
Razane Tajeddine, Oliver W. Gnilke, David Karpuk +2
The problem of Private Information Retrieval (PIR) from coded storage systems with colluding, byzantine, and unresponsive servers is considered. An explicit scheme using an …
Robust Private Information Retrieval from Coded Systems with Byzantine and Colluding Servers
Razane Tajeddine, Oliver W. Gnilke, David Karpuk +2
A private information retrieval (PIR) scheme on coded storage systems with colluding, byzantine, and non-responsive servers is presented. Furthermore, the scheme can also be used f…
Robust Private Information Retrieval on Coded Data
Razane Tajeddine, Salim El Rouayheb
We consider the problem of designing PIR scheme on coded data when certain nodes are unresponsive. We provide the construction of -robust PIR schemes that can tolerate up to …
Private Information Retrieval Schemes for Coded Data with Arbitrary Collusion Patterns
Razane Tajeddine, Oliver W. Gnilke, David Karpuk +3
In Private Information Retrieval (PIR), one wants to download a file from a database without revealing to the database which file is being downloaded. Much attention has been paid…
Private Information Retrieval from MDS Coded Data in Distributed Storage Systems
Razan Tajeddine, Oliver W. Gnilke, Salim El Rouayheb
The problem of providing privacy, in the private information retrieval (PIR) sense, to users requesting data from a distributed storage system (DSS), is considered. The DSS is code…