Related papers: Improving Google A2A Protocol: Protecting Sensitiv…
The development of privacy-enhancing technologies has made immense progress in reducing trade-offs between privacy and performance in data exchange and analysis. Similar tools for structured transparency could be useful for AI governance by…
The integration of artificial intelligence (AI) into telecommunications infrastructure introduces novel risks, such as algorithmic bias and unpredictable system behavior, that fall outside the scope of traditional cybersecurity and data…
Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual…
Large Language Model (LLM)-based agents increasingly interact, collaborate, and delegate tasks to one another autonomously with minimal human interaction. Industry guidelines for agentic system governance emphasize the need for users to…
The rapid development of large language models (LLMs) has led to the widespread deployment of LLM agents across diverse industries, including customer service, content generation, data analysis, and even healthcare. However, as more LLM…
Due to the wide application of average consensus algorithm, its security and privacy problems have attracted great attention. In this paper, we consider the system threatened by a set of unknown agents that are both "malicious" and…
AI assistants are increasingly integrated into older adults' daily lives, offering new opportunities for social support and accessibility while raising important questions about privacy, autonomy, and trust. As these systems become embedded…
Artificial intelligence (AI) models introduce privacy vulnerabilities to systems. These vulnerabilities may impact model owners or system users; they exist during model development, deployment, and inference phases, and threats can be…
Agentic AI systems are increasingly capable of performing professional and personal tasks with limited human involvement. However, tracking these developments is difficult because the AI agent ecosystem is complex, rapidly evolving, and…
Communication stands as a potent mechanism to harmonize the behaviors of multiple agents. However, existing works primarily concentrate on broadcast communication, which not only lacks practicality, but also leads to information redundancy.…
Orchestrated multi-agent systems represent the next stage in the evolution of artificial intelligence, where autonomous agents collaborate through structured coordination and communication to achieve complex, shared objectives. This paper…
As 6G evolves into an AI-native technology, the integration of artificial intelligence (AI) and Generative AI into cellular communication systems presents unparalleled opportunities for enhancing connectivity, network optimization, and…
Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…
Large Language Models (LLMs) are increasingly deployed as autonomous agents, yet their practical utility is fundamentally constrained by a limited context window and state desynchronization resulting from the LLMs' stateless nature and…
Robotics and automation are poised to change the landscape of home and work in the near future. Robots are adept at deliberately moving, sensing, and interacting with their environments. The pervasive use of this technology promises…
Continuous Authentication (CA) has been proposed as a potential solution to counter complex cybersecurity attacks that exploit conventional static authentication mechanisms that authenticate users only at an ingress point. However, widely…
With the rapidly increasing number of bandwidth-intensive terminals capable of intelligent computing and communication, such as smart devices equipped with shallow neural network models, the complexity of multiple access for these…
Pre-trained large language models, such as GPT\nobreakdash-2 and BERT, are often fine-tuned to achieve state-of-the-art performance on a downstream task. One natural example is the ``Smart Reply'' application where a pre-trained model is…
As data privacy continues to be a crucial human-right concern as recognized by the UN, regulatory agencies have demanded developers obtain user permission before accessing user-sensitive data. Mainly through the use of privacy policies…
Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web,…