Related papers: Bandwidth-efficient Storage Services for Mitigatin…
We study privacy in a distributed learning framework, where clients collaboratively build a learning model iteratively through interactions with a server from whom we need privacy. Motivated by stochastic optimization and the federated…
With the rise of Software-Defined Networking (SDN) for managing traffic and ensuring seamless operations across interconnected devices, challenges arise when SDN controllers share infrastructure with deep learning (DL) workloads. Resource…
While reconfigurable intelligent surface (RIS) technology has been shown to provide numerous benefits to wireless systems, in the hands of an adversary such technology can also be used to disrupt communication links. This paper describes…
Erasure coding is widely used for massive storage in data centers to achieve high fault tolerance and low storage redundancy. Since the cross-rack communication cost is often high, it is critical to design erasure codes that minimize the…
Current LLM safety defenses fail under decomposition attacks, where a malicious goal is decomposed into benign subtasks that circumvent refusals. The challenge lies in the existing shallow safety alignment techniques: they only detect harm…
Privacy-Preserving Machine Learning algorithms must balance classification accuracy with data privacy. This can be done using a combination of cryptographic and machine learning tools such as Convolutional Neural Networks (CNN). CNNs…
Data privacy has become an increasingly important issue in Machine Learning (ML), where many approaches have been developed to tackle this challenge, e.g. cryptography (Homomorphic Encryption (HE), Differential Privacy (DP), etc.) and…
A recent trend in cryptography is to protect data and computation against various side-channel attacks. Dziembowski and Faust (TCC 2012) have proposed a general way to protect arbitrary circuits against any continual leakage assuming that:…
The evolution of the future beyond-5G/6G networks towards a service-aware network is based on network slicing technology. With network slicing, communication service providers seek to meet all the requirements imposed by the verticals,…
Local differential privacy (LDP) enables the efficient release of aggregate statistics without having to trust the central server (aggregator), as in the central model of differential privacy, and simultaneously protects a client's…
Recurrent Neural Networks (RNNs) yield attractive properties for constructing Intrusion Detection Systems (IDSs) for network data. With the rise of ubiquitous Machine Learning (ML) systems, malicious actors have been catching up quickly to…
This article investigates the security issue caused by false data injection attacks in distributed estimation, wherein each sensor can construct two types of residues based on local estimates and neighbor information, respectively. The…
In this paper, we study distributed storage problems over unidirectional ring networks. A lower bound on the reconstructing bandwidth to recover total original data for each user is proposed, and it is achievable for arbitrary parameters.…
Fundamental rate-distortion-perception (RDP) trade-offs arise in applications requiring maintained perceptual quality of reconstructed data, such as neural image compression. When compressed data is transmitted over public communication…
Network slicing is the key to enable virtualized resource sharing among vertical industries in the era of 5G communication. Efficient resource allocation is of vital importance to realize network slicing in real-world business scenarios. To…
Backup storage systems often remove redundancy across backups via inline deduplication, which works by referring duplicate chunks of the latest backup to those of existing backups. However, inline deduplication degrades restore performance…
The widespread deployment of LLMs across enterprise services has created a critical security blind spot. Organizations operate multiple LLM services handling billions of queries daily, yet regulatory compliance boundaries prevent these…
Resource reservation is an essential step to enable wireless data networks to support a wide range of user demands. In this paper, we consider the problem of joint resource reservation in the backhaul and Radio Access Network (RAN) based on…
Data parallelism has become a dominant method to scale Deep Neural Network (DNN) training across multiple nodes. Since synchronizing a large number of gradients of the local model can be a bottleneck for large-scale distributed training,…
Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. Only processed or `smashed' data can be transmitted from the clients to the server during the SL…