Related papers: Analysis of Efficiency of the Messaging Layer Secu…

Aggregating Message Authentication Codes (MACs) promises to save valuable bandwidth in resource-constrained environments. The idea is simple: Instead of appending an authentication tag to each message in a communication stream, the…

The fields of machine learning (ML) and cryptanalysis share an interestingly common objective of creating a function, based on a given set of inputs and outputs. However, the approaches and methods in doing so vary vastly between the two…

Secure Multi-Party Computation (SMC) allows parties with similar background to compute results upon their private data, minimizing the threat of disclosure. The exponential increase in sensitive data that needs to be passed upon networked…

Tabletop exercises are a crucial component of many company's strategy to test and evaluate its preparedness for security incidents in a realistic way. Traditionally led by external firms specializing in cybersecurity, these exercises can be…

Answering end user security questions is challenging. While large language models (LLMs) like GPT, LLAMA, and Gemini are far from error-free, they have shown promise in answering a variety of questions outside of security. We studied LLM…

Ultra-reliable and low-latency communication (URLLC) is one category of service to be provided by next-generation wireless networks. Motivated by increasing security concerns in such networks, this article focuses on physical layer security…

Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, which amplifies the…

Research shows that dialogue, the interactive process through which participants articulate their thinking, plays a central role in constructing shared understanding, coordinating action, and shaping learning outcomes in teams. Analysing…

Quantum secret sharing (QSS) plays a significant role in multiparty quantum communication and is a crucial component of future quantum multiparty computing networks. Therefore, it is highly valuable to develop a QSS protocol that offers…

Large language models (LLMs) have achieved remarkable progress across domains and applications but face challenges such as high fine-tuning costs, inference latency, limited edge deployability, and reliability concerns. Small language…

This paper investigates the physical layer security (PLS) performance of $\alpha$-$\mathcal{F}$ fading channels with pointing errors under passive and active eavesdropping scenarios. Novel analytical expressions are derived for key PLS…

Strongly multiplicative linear secret sharing schemes (LSSS) have been a powerful tool for constructing secure multiparty computation protocols. However, it remains open whether or not there exist efficient constructions of strongly…

Recently, many organizations have been installing middleboxes in their networks in large numbers to provide various services to their customers. Although middleboxes have the advantage of not being dependent on specific hardware and being…

Cascade systems route computational requests to smaller models when possible and defer to larger models only when necessary, offering a promising approach to balance cost and quality in LLM deployment. However, they face a fundamental…

Machine learning models are susceptible to membership inference attacks (MIAs), which aim to infer whether a sample is in the training set. Existing work utilizes gradient ascent to enlarge the loss variance of training data, alleviating…

Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are…

We study the inherent trade-offs in minimizing privacy risks and maximizing utility, while maintaining high computational efficiency, when fine-tuning large language models (LLMs). A number of recent works in privacy research have attempted…

Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet companies to deploy machine learning as a service (MLaaS).…

Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we…

Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and…