20 citations · 27 across the 15 of their papers we have counts for
19 papers
Watermarkability: Measuring and Improving Language-Model Compatibility with Logit-Based Watermarks
Zewei Deng, Mohamed Seif, Liyan Xie
Language-model watermarks can help identify model-generated text, encode provenance information, and detect post-generation edits. A broad class of logit-based watermarks increases…
NOEMA: Executable Contracts for Learned Wireless Comparisons
Mostafa Naseri, Mohamed Seif, H. Vincent Poor +1
Learning-based wireless research increasingly combines simulation, external model training, and benchmarking. Rebuilding these stages for every experiment is time-consuming, while…
Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting Codes
Zewei Deng, Muhammad Siddeek, Liyan Xie +4
LLM watermarking has become an effective approach to distinguishing AI-generated text from human-written text by embedding detectable patterns during generation. However, a small p…
When Phase Doesn't Matter: Self-Coherent Over-the-Air Computation at Sub-THz
Sherif Ghozzy, Mohamed Seif, H. Vincent Poor +1
Over-the-air computation (OAC) enables efficient function aggregation in wireless networks by exploiting the superposition property of the multiple-access channel. However, practic…
Toward Autonomous O-RAN: A Multi-Scale Agentic AI Framework for Real-Time Network Control and Management
Hojjat Navidan, Mohammad Cheraghinia, Jaron Fontaine +5
Open Radio Access Networks (O-RAN) promise flexible 6G network access through disaggregated, software-driven components and open interfaces, but this programmability also increases…
Protecting Human Activity Signatures in Compressed IEEE 802.11 CSI Feedback
Mohamed Seif, Atsutse Kludze, Yasaman Ghasempour +3
Explicit channel state information (CSI) feedback in IEEE~802.11 conveys \emph{transmit beamforming directions} by reporting quantized Givens rotation and phase angles that paramet…
Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial Watermarking
Liyan Xie, Muhammad Siddeek, Mohamed Seif +2
Watermarking has become a key technique for proprietary language models, enabling the distinction between AI-generated and human-written text. However, in many real-world scenarios…
Adversary-Aware Private Inference over Wireless Channels
Mohamed Seif, Malcolm Egan, Andrea J. Goldsmith +1
AI-based sensing at wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for vision and perception tasks such as…
Differentially Private Spectral Graph Clustering: Balancing Privacy, Accuracy, and Efficiency
Antti Koskela, Mohamed Seif, H. Vincent Poor +1
We study spectral graph clustering under edge differential privacy. We propose a matrix shuffling mechanism that combines randomized edge flipping with a random permutation of the…
Federated Learning-Enabled Hybrid Language Models for Communication-Efficient Token Transmission
Faranaksadat Solat, Joohyung Lee, Mohamed Seif +2
Hybrid Language Models (HLMs) combine the low-latency efficiency of Small Language Models (SLMs) on edge devices with the high accuracy of Large Language Models (LLMs) on centraliz…
On the Price of Differential Privacy for Spectral Clustering over Stochastic Block Models
Antti Koskela, Mohamed Seif, Andrea J. Goldsmith
We investigate privacy-preserving spectral clustering for community detection within stochastic block models (SBMs). Specifically, we focus on edge differential privacy (DP) and pr…
How Can Incentives and Cut Layer Selection Influence Data Contribution in Split Federated Learning?
Joohyung Lee, Jungchan Cho, Wonjun Lee +2
To alleviate the training burden in federated learning while enhancing convergence speed, Split Federated Learning (SFL) has emerged as a promising approach by combining the advant…
Deep Learning-Based Image Compression for Wireless Communications: Impacts on Reliability,Throughput, and Latency
Mostafa Naseri, Pooya Ashtari, Mohamed Seif +3
In wireless communications, efficient image transmission must balance reliability, throughput, and latency, especially under dynamic channel conditions. This paper presents an adap…
Privacy Preserving Semi-Decentralized Mean Estimation over Intermittently-Connected Networks
Rajarshi Saha, Mohamed Seif, Michal Yemini +2
We consider the problem of privately estimating the mean of vectors distributed across different nodes of an unreliable wireless network, where communications between nodes can fai…
Over-the-Air Collaborative Inference with Feature Differential Privacy
Mohamed Seif, Yuqi Nie, Andrea Goldsmith +1
Collaborative inference in next-generation networks can enhance Artificial Intelligence (AI) applications, including autonomous driving, personal identification, and activity class…
Differentially Private Online Community Detection for Censored Block Models: Algorithms and Fundamental Limits
Mohamed Seif, Liyan Xie, Andrea J. Goldsmith +1
We study the private online change detection problem for dynamic communities, using a censored block model (CBM). We consider edge differential privacy (DP) in both local and centr…
Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learning
Joohyung Lee, Mohamed Seif, Jungchan Cho +1
Split Federated Learning (SFL) has recently emerged as a promising distributed learning technology, leveraging the strengths of both federated and split learning. It emphasizes the…
Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy
Rajarshi Saha, Mohamed Seif, Michal Yemini +2
This work considers the problem of Distributed Mean Estimation (DME) over networks with intermittent connectivity, where the goal is to learn a global statistic over the data sampl…
Achievable Degrees of Freedom of the K-user MISO Broadcast Channel with Alternating CSIT via Interference Creation-Resurrection
Mohamed Seif, Amr El-Keyi, Mohammed Nafie
Channel state information at the transmitter affects the degrees of freedom of the wireless networks. In this paper, we analyze the DoF for the K-user multiple-input single-output…