English
Related papers

Related papers: Contextualized Privacy Defense for LLM Agents

200 papers

Technology is shaping our lives in a multitude of ways. This is fuelled by a technology infrastructure, both legacy and state of the art, composed of a heterogeneous group of hardware, software, services and organisations. Such…

Cryptography and Security · Computer Science 2023-01-18 Julia A. Meister , Raja Naeem Akram , Konstantinos Markantonakis

As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. Recent work shows that text optimizers can produce jailbreaking prompts that bypass moderation and alignment. Drawing from…

Compared to traditional models, agentic AI represents a highly valuable target for potential attackers as they possess privileged access to data sources and API tools, which are traditionally not incorporated into classical agents. Unlike a…

Artificial Intelligence · Computer Science 2025-09-24 Tom Pawelek , Raj Patel , Charlotte Crowell , Noorbakhsh Amiri , Sudip Mittal , Shahram Rahimi , Andy Perkins

Large language models (LLMs) demonstrate remarkable medical expertise, but data privacy concerns impede their direct use in healthcare environments. Although offering improved data privacy protection, domain-specific small language models…

Computation and Language · Computer Science 2024-05-17 Xinlu Zhang , Shiyang Li , Xianjun Yang , Chenxin Tian , Yao Qin , Linda Ruth Petzold

We present substantial evidence demonstrating the benefits of integrating Large Language Models (LLMs) with a Contextual Multi-Armed Bandit framework. Contextual bandits have been widely used in recommendation systems to generate…

Machine Learning · Computer Science 2024-10-30 Parand A. Alamdari , Yanshuai Cao , Kevin H. Wilson

As Large Language Models (LLMs) are increasingly deployed in sensitive domains such as enterprise and government, ensuring that they adhere to user-defined security policies within context is critical-especially with respect to information…

Computation and Language · Computer Science 2025-09-17 Hwan Chang , Yumin Kim , Yonghyun Jun , Hwanhee Lee

Large language models (LLMs) possess extensive knowledge bases and strong reasoning capabilities, making them promising tools for complex, multi-agent planning in embodied environments. However, despite LLMs' advanced abilities and the…

Multiagent Systems · Computer Science 2025-06-10 Xinran Li , Chenjia Bai , Zijian Li , Jiakun Zheng , Ting Xiao , Jun Zhang

Large Language Models (LLMs) are widely used by students, yet their tendency to provide fast and complete answers may discourage reflection and foster overconfidence. We examined how alternative LLM interaction designs support deeper…

Human-Computer Interaction · Computer Science 2026-04-13 Elena Eleftheriou , George Pallis , Marios Constantinides

In this paper, localized information privacy (LIP) is proposed, as a new privacy definition, which allows statistical aggregation while protecting users' privacy without relying on a trusted third party. The notion of context-awareness is…

Information Theory · Computer Science 2018-08-02 Bo Jiang , Ming Li , Ravi Tandon

As multi-agent systems proliferate, there is increasing demand for coordination protocols that protect agents' sensitive information while allowing them to collaborate. To help address this need, this paper presents a differentially private…

Optimization and Control · Mathematics 2020-09-15 Calvin Hawkins , Matthew Hale

Deep learning techniques based on neural networks have shown significant success in a wide range of AI tasks. Large-scale training datasets are one of the critical factors for their success. However, when the training datasets are…

Cryptography and Security · Computer Science 2019-12-23 Lei Yu , Ling Liu , Calton Pu , Mehmet Emre Gursoy , Stacey Truex

In the evolving landscape of human-centric systems, personalized privacy solutions are becoming increasingly crucial due to the dynamic nature of human interactions. Traditional static privacy models often fail to meet the diverse and…

Machine Learning · Computer Science 2024-11-14 Mojtaba Taherisadr , Salma Elmalaki

The rise of Large Language Model (LLM) agents, augmented with tool use, skills, and external knowledge, has introduced new security risks. Among them, prompt injection attacks, where adversaries embed malicious instructions into the agent…

Cryptography and Security · Computer Science 2026-05-06 Shihao Weng , Yang Feng , Jinrui Zhang , Xiaofei Xie , Jiongchi Yu , Jia Liu

With the rise of large language models (LLMs), ensuring they embody the principles of being helpful, honest, and harmless (3H), known as Human Alignment, becomes crucial. While existing alignment methods like RLHF, DPO, etc., effectively…

Computation and Language · Computer Science 2024-04-02 Shu Yang , Jiayuan Su , Han Jiang , Mengdi Li , Keyuan Cheng , Muhammad Asif Ali , Lijie Hu , Di Wang

The growing number of applications of Reinforcement Learning (RL) in real-world domains has led to the development of privacy-preserving techniques due to the inherently sensitive nature of data. Most existing works focus on differential…

Machine Learning · Computer Science 2021-09-20 Alberto Jesu , Victor-Alexandru Darvariu , Alessandro Staffolani , Rebecca Montanari , Mirco Musolesi

We introduce a multi-turn benchmark for evaluating personalised alignment in LLM-based AI assistants, focusing on their ability to handle user-provided safety-critical contexts. Our assessment of ten leading models across five scenarios…

Human-Computer Interaction · Computer Science 2025-01-31 Lize Alberts , Benjamin Ellis , Andrei Lupu , Jakob Foerster

Distributed multi-agent learning enables agents to cooperatively train a model without requiring to share their datasets. While this setting ensures some level of privacy, it has been shown that, even when data is not directly shared, the…

Machine Learning · Computer Science 2021-06-03 Anudit Nagar , Cuong Tran , Ferdinando Fioretto

In recent years, Large-Language-Model-driven AI agents have exhibited unprecedented intelligence and adaptability. Nowadays, agents are undergoing a new round of evolution. They no longer act as an isolated island like LLMs. Instead, they…

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions…

Artificial Intelligence · Computer Science 2026-05-05 Sheldon Yu , Yingcheng Sun , Hanqing Guo , Julian McAuley , Qianqian Tong

Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice. One recent popular approach to study these concerns is using the differential privacy via a…

Cryptography and Security · Computer Science 2020-07-29 Lichao Sun , Ji Wang , Philip S. Yu , Lifang He