Related papers: Undetectable Conversations Between AI Agents via P…
This paper proposes a comprehensive framework for the generation of covert advertisements within Conversational AI systems, along with robust techniques for their detection. It explores how subtle promotional content can be crafted within…
The rise of agentic systems that combine orchestration, tool use, and conversational capabilities, has been more visible by the recent advent of large language models (LLMs). While open-domain frameworks exist, applying them in private…
Multi-agent systems using large language models (LLMs) have demonstrated impressive capabilities across various domains. However, current agent communication suffers from verbose output that overload context and increase computational…
Automatic speech recognition systems have created exciting possibilities for applications, however they also enable opportunities for systematic eavesdropping. We propose a method to camouflage a person's voice over-the-air from these…
Key-agreement protocols whose security is proven in the random oracle model are an important alternative to protocols based on public-key cryptography. In the random oracle model, the parties and the eavesdropper have access to a shared…
Multi-agent discussions have been widely adopted, motivating growing efforts to develop attacks that expose their vulnerabilities. In this work, we study a practical yet largely unexplored attack scenario, the discussion-monitored scenario,…
In the coming decade, artificial intelligence systems will continue to improve and revolutionise every industry and facet of human life. Designing effective, seamless and symbiotic communication paradigms between humans and AI agents is…
Personalized AI agents rely on access to a user's digital footprint, which often includes sensitive data from private emails, chats and purchase histories. Yet this access creates a fundamental societal and privacy risk: systems lacking…
We examine the problem of learning to cooperate in the context of wireless communication. In our setting, two agents must learn modulation schemes that enable them to communicate across a power-constrained additive white Gaussian noise…
We focus on human-robot collaborative transport, in which a robot and a user collaboratively move an object to a goal pose. In the absence of explicit communication, this problem is challenging because it demands tight implicit coordination…
Silent speech interface (SSI) enables hands-free input without audible vocalization, but most SSI systems do not verify speaker identity. We present HEar-ID, which uses consumer active noise-canceling earbuds to capture low-frequency…
Non-interactive key exchange (NIKE) enables two or multiple parties (just knowing the public system parameters and each other's public key) to derive a (group) session key without the need for interaction. Recently, NIKE in multi-party…
Data collecting agents in large networks, such as the electric power system, need to share information (measurements) for estimating the system state in a distributed manner. However, privacy concerns may limit or prevent this exchange…
Secrecy transmission is investigated for a cooperative jamming scheme, where a multi-antenna jam-mer generates artificial noise (AN) to confuse eavesdroppers. Two kinds of eavesdroppers are considered: passive eavesdroppers who only…
We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our work. We provide a review of the…
We propose a light-weight client-server model of communication between program analyses. Clients are individual analyses and the server mediates their communication. A client cannot see properties of any other and the communication is…
Effective human-AI collaboration on complex reasoning tasks requires that users understand and interact with the model's process, not just receive an output. However, the monolithic text from methods like Chain-of-Thought (CoT) prevents…
This article presents a modular, component-based architecture for developing and evaluating AI agents that bridge the gap between natural language interfaces and complex enterprise data warehouses. The system directly addresses core…
This paper investigates how natural language communication with an AI agent affects human cooperative behaviour in indefinitely repeated Prisoner's Dilemma games. We conduct a laboratory experiment (n = 126) with two between-subjects…
Symbols are shared, but perception is private. We study emergent communication between heterogeneous visual agents through decentralized learning, asking what visual information can become shareable when agents have different visual…