Related papers: Centralized vs Decentralized Targeted Brute-Force …
We consider a multi-armed bandit setting that is inspired by real-world applications in e-commerce. In our setting, there are a few types of users, each with a specific response to the different arms. When a user enters the system, his type…
Current backdoor defense methods are evaluated against a single attack at a time. This is unrealistic, as powerful machine learning systems are trained on large datasets scraped from the internet, which may be attacked multiple times by one…
Side-channel attacks on memory (SCAM) exploit unintended data leaks from memory subsystems to infer sensitive information, posing significant threats to system security. These attacks exploit vulnerabilities in memory access patterns, cache…
Rank aggregation with pairwise comparisons is widely encountered in sociology, politics, economics, psychology, sports, etc . Given the enormous social impact and the consequent incentives, the potential adversary has a strong motivation to…
In Cyber-Physical Systems (CPSs), inference based on communicated data is of critical significance as it can be used to manipulate or damage the control operations by adversaries. This calls for efficient mechanisms for secure transmission…
In distributed wireless networks, nodes often do not know the topology (network size, connectivity and the channel gains) of the network. Thus, they have to compute their transmission and reception parameters in a distributed fashion. In…
Coordinated campaigns are used to influence and manipulate social media platforms and their users, a critical challenge to the free exchange of information online. Here we introduce a general, unsupervised network-based methodology to…
In this paper, we derive information-theoretic performance limits for secure and reliable communications over the general two-user discrete memoryless broadcast channel with side-information at the transmitter. The sender wishes to…
Network coding is an elegant technique where, instead of simply relaying the packets of information they receive, the nodes of a network are allowed to combine \emph{several} packets together for transmission and this technique can be used…
In this work, we study two problems: three-user Multiple-Access Channel (MAC) with correlated sources, and MAC with Feedback (MAC-FB) with independent messages. For the first problem, we identify a structure in the joint probability…
The side-channel attack is an attack method based on the information gained about implementations of computer systems, rather than weaknesses in algorithms. Information about system characteristics such as power consumption, electromagnetic…
Local differential privacy is a widely studied restriction on distributed algorithms that collect aggregates about sensitive user data, and is now deployed in several large systems. We initiate a systematic study of a fundamental limitation…
Design and manufacturing of integrated circuits predominantly use a globally distributed semiconductor supply chain involving diverse entities. The modern semiconductor supply chain has been designed to boost production efficiency, but is…
The problem of distributed binary hypothesis testing in the Gray-Wyner network with side information is studied in this paper. An observer has access to a discrete memoryless and stationary source and describes its observation to two…
As large-scale theft of data from corporate servers is becoming increasingly common, it becomes interesting to examine alternatives to the paradigm of centralizing sensitive data into large databases. Instead, one could use cryptography and…
In recent years, various deep learning techniques have been exploited in side channel attacks, with the anticipation of obtaining more appreciable attack results. Most of them concentrate on improving network architectures or putting…
This paper considers a distributed optimization problem in a multi-agent system where a fraction of the agents act in an adversarial manner. Specifically, the malicious agents steer the network of agents away from the optimal solution by…
A key challenge of big data analytics is how to collect a large volume of (labeled) data. Crowdsourcing aims to address this challenge via aggregating and estimating high-quality data (e.g., sentiment label for text) from pervasive…
It is important to study the risks of publishing privacy-sensitive data. Even if sensitive identities (e.g., name, social security number) were removed and advanced data perturbation techniques were applied, several de-anonymization attacks…
Recent work has shown that graph neural networks (GNNs) are vulnerable to adversarial attacks on graph data. Common attack approaches are typically informed, i.e. they have access to information about node attributes such as labels and…