Related papers: Anonymous On-line Communication Between Program An…

Human communication is often implicit, conveying tone, identity, and intent beyond literal meanings. While large language models have achieved strong performance on explicit tasks such as summarization and reasoning, their capacity for…

In this paper, we propose a protocol that preserves (statistical) privacy of agents' costs in peer-to-peer distributed optimization against a passive adversary that corrupts certain number of agents in the network. The proposed protocol…

Conversational agents are increasingly woven into individuals' personal lives, yet users often underestimate the privacy risks associated with them. The moment users share information with these agents-such as large language models…

Motivated by recent developments in the shuffle model of differential privacy, we propose a new approximate shuffling functionality called Alternating Shuffle, and provide a protocol implementing alternating shuffling in a single-server…

Speech emotion sensing in communication networks has a wide range of applications in real life. In these applications, voice data are transmitted from the user to the central server for storage, processing, and decision making. However,…

The development of AI agents based on large, open-domain language models (LLMs) has paved the way for the development of general-purpose AI assistants that can support human in tasks such as writing, coding, graphic design, and scientific…

We present a relational MPC framework for secure collaborative analytics on private data with no information leakage. Our work targets challenging use cases where data owners may not have private resources to participate in the computation,…

Many intelligent systems currently interact with others using at least one of fixed communication inputs or preset responses, resulting in rigid interaction experiences and extensive efforts developing a variety of scenarios for the system.…

Social aspects in software development teams are of particular importance for a successful project closure. To analyze sentiments in software projects, there are several tools and approaches available. These tools analyze text-based…

Recommender systems trained on offline historical user behaviors are embracing conversational techniques to online query user preference. Unlike prior conversational recommendation approaches that systemically combine conversational and…

We often assume that agent-to-agent interaction will mirror human conversation. However, agents operate fundamentally differently. What if they could develop communication patterns that are more efficient and better aligned with their…

In various economic environments, people observe other people with whom they strategically interact. We can model such information-sharing relations as an information network, and the strategic interactions as a game on the network. When…

We model the communication of narratives as a cheap-talk game under model uncertainty. The sender has private information about the true data generating process of publicly observable data. The receiver is uncertain about how to interpret…

In multi-agent planning, agents jointly compute a plan that achieves mutual goals, keeping certain information private to the individual agents. Agents' coordination is achieved through the transmission of messages. These messages can be a…

We study a simple but compelling model of $n$ interacting agents via time-dependent, unidirectional communication. The model finds wide application in a variety of fields including synchronization, swarming and distributed decision making.…

While both agent interaction and personalisation are vibrant topics in research on large language models (LLMs), there has been limited focus on the effect of language interaction on the behaviour of persona-conditioned LLM agents. Such an…

Existing personalized dialogue models use human designed persona descriptions to improve dialogue consistency. Collecting such descriptions from existing dialogues is expensive and requires hand-crafted feature designs. In this paper, we…

This work considers the problem of mitigating information leakage between communication and sensing in systems jointly performing both operations. Specifically, a discrete memoryless state-dependent broadcast channel model is studied in…

We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator. We propose to train personalized models…

The problem of controlling multi-agent systems under different models of information sharing among agents has received significant attention in the recent literature. In this paper, we consider a setup where rather than committing to a…