Related papers: Minimizing Information Leakage under Padding Const…
Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…
Random linear network coding can be used in peer-to-peer networks to increase the efficiency of content distribution and distributed storage. However, these systems are particularly susceptible to Byzantine attacks. We quantify the impact…
For many differentially private algorithms, such as the prominent noisy stochastic gradient descent (DP-SGD), the analysis needed to bound the privacy leakage of a single training run is well understood. However, few studies have reasoned…
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…
Using a broadcast channel to transmit clients' data requests may impose privacy risks. In this paper, we address such privacy concerns in the index coding framework. We show how a malicious client can infer some information about the…
While sharing files in a peer-to-peer (P2P) system significantly increases both the speed of retrieving the contents and the robustness of the system, tracing the access of files is not straightforward, even in the case of private P2P…
We consider the setting of a master server who possesses confidential data (genomic, medical data, etc.) and wants to run intensive computations on it, as part of a machine learning algorithm for example. The master wants to distribute…
Privacy leaks are an unfortunate and an integral part of the current Internet domain name resolution. Each DNS query generated by a user reveals -- to one or more DNS servers -- the origin and target of that query. Over time, a user's…
Large Language Models (LLMs) excel in natural language understanding by capturing hidden semantics in vector space. This process enriches the value of text embeddings for various downstream tasks, thereby fostering the…
In this paper, we address the problem of secure distributed computation in scenarios where user data is not uniformly distributed, extending existing frameworks that assume uniformity, an assumption that is challenging to enforce in data…
In network communications, information transmission often encounters wiretapping attacks. Secure network coding is introduced to prevent information from being leaked to adversaries. The investigation of performance bounds on the numbers of…
Algorithmic fairness and privacy are essential pillars of trustworthy machine learning. Fair machine learning aims at minimizing discrimination against protected groups by, for example, imposing a constraint on models to equalize their…
With the popularity of smartphones, mobile applications (apps) have penetrated the daily life of people. Although apps provide rich functionalities, they also access a large amount of personal information simultaneously. As a result,…
It is well known that apps running on mobile devices extensively track and leak users' personally identifiable information (PII); however, these users have little visibility into PII leaked through the network traffic generated by their…
Side channels represent a broad class of security vulnerabilities that have been demonstrated to exist in many applications. Because completely eliminating side channels often leads to prohibitively high overhead, there is a need for a…
Information leakage is becoming a critical problem as various information becomes publicly available by mistake, and machine learning models train on that data to provide services. As a result, one's private information could easily be…
A privacy mechanism design problem is studied through the lens of information theory. In this work, an agent observes useful data $Y=(Y_1,...,Y_N)$ that is correlated with private data $X=(X_1,...,X_N)$ which is assumed to be also…
In the federated learning system, parameter gradients are shared among participants and the central modulator, while the original data never leave their protected source domain. However, the gradient itself might carry enough information…
Privacy is an individual choice to determine which personal details can be collected, used and shared. Individual consent and transparency are the core tenets for earning customers trust and this motivates the organizations to adopt privacy…
The inevitable leakage of privacy as a result of unrestrained disclosure of personal information has motivated extensive research on robust privacy-preserving mechanisms. However, existing research is mostly limited to solving the problem…