Related papers: Improving Bitswap Privacy with Forwarding and Sour…

Decentralized optimization is increasingly popular in machine learning for its scalability and efficiency. Intuitively, it should also provide better privacy guarantees, as nodes only observe the messages sent by their neighbors in the…

The critical role played by email has led to a range of extension protocols (e.g., SPF, DKIM, DMARC) designed to protect against the spoofing of email sender domains. These protocols are complex as is, but are further complicated by…

The cloud model's dependence on massive parallelism and resource sharing exacerbates the security challenge of timing side-channels. Timing Information Flow Control (TIFC) is a novel adaptation of IFC techniques that may offer a way to…

Network embedding represents network nodes by a low-dimensional informative vector. While it is generally effective for various downstream tasks, it may leak some private information of networks, such as hidden private links. In this work,…

Many popular applications use traces of user data to offer various services to their users. However, even if user data is anonymized and obfuscated, a user's privacy can be compromised through the use of statistical matching techniques that…

In this work, we study information leakage in timing side channels that arise in the context of shared event schedulers. Consider two processes, one of them an innocuous process (referred to as Alice) and the other a malicious one (referred…

In this work we describe a token-based solution to Contact Tracing via Distributed Point Functions (DPF) and, more generally, Function Secret Sharing (FSS). The key idea behind the solution is that FSS natively supports secure keyword…

Machine learning is increasingly used for intrusion detection in IoT networks. This paper explores the effectiveness of using individual packet features (IPF), which are attributes extracted from a single network packet, such as timing,…

Federated learning (FL) has emerged as a collaborative approach that allows multiple clients to jointly learn a machine learning model without sharing their private data. The concern about privacy leakage, albeit demonstrated under specific…

We study the ON-OFF privacy problem. At each time, the user is interested in the latest message of one of $N$ sources. Moreover, the user is assumed to be incentivized to turn privacy ON or OFF whether he/she needs it or not. When privacy…

Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more…

Matrix factorization is one of the most commonly used technologies in recommendation system. With the promotion of recommendation system in e-commerce shopping, online video and other aspects, distributed recommendation system has been…

Decentralized unpermissioned peer-to-peer networks are inherently vulnerable to spam when they allow arbitrary participants to submit content to a common public index or registry; preventing this is difficult due to the absence of a central…

The decentralized nature of federated learning, that often leverages the power of edge devices, makes it vulnerable to attacks against privacy and security. The privacy risk for a peer is that the model update she computes on her private…

Global corporations (e.g., Google and Microsoft) have recently introduced a new model of cloud services, fuzzing-as-a-service (FaaS). Despite effectively alleviating the cost of fuzzing, the model comes with privacy concerns. For example,…

This paper introduces a novel privacy-preservation framework named PFID for LLMs that addresses critical privacy concerns by localizing user data through model sharding and singular value decomposition. When users are interacting with LLM…

Crowdsourced data used in machine learning services might carry sensitive information about attributes that users do not want to share. Various methods have been proposed to minimize the potential information leakage of sensitive attributes…

In the fight against tax evaders and other cheats, governments seek to gather more information about their citizens. In this paper we claim that this increased transparency, combined with ineptitude, or corruption, can lead to widespread…

Next-generation systems aim to increase both the speed and responsiveness of wireless communications, while supporting compelling applications such as edge and cloud computing, remote-Health, vehicle-to-infrastructure communications, etc.…

This paper considers random walk-based decentralized learning, where at each iteration of the learning process, one user updates the model and sends it to a randomly chosen neighbor until a convergence criterion is met. Preserving data…