Related papers: SRPG: Semantically Reconstructed Privacy Guard for…

LLM-based multi-agent systems (LLM-MAS) have become a promising paradigm for solving complex tasks through role specialization, tool use, memory, and collaborative reasoning. However, these interactions create new security risks that…

As large language models are increasingly deployed in sensitive environments, fingerprinting attacks pose significant privacy and security risks. We present a study of LLM fingerprinting from both offensive and defensive perspectives. Our…

The indexing-retrieval-generation paradigm of retrieval-augmented generation (RAG) has been highly successful in solving knowledge-intensive tasks by integrating external knowledge into large language models (LLMs). However, the…

Recent progress in artificial intelligence (AI), particularly in the domain of large language models (LLMs), has resulted in powerful and versatile dual-use systems. This intelligence can be put towards a wide variety of beneficial tasks,…

Semi-supervised learning (SSL) tackles the label missing problem by enabling the effective usage of unlabeled data. While existing SSL methods focus on the traditional setting, a practical and challenging scenario called label Missing Not…

Recent advances in Large Language Models (LLMs) have led to the widespread adoption of third-party inference services, raising critical privacy concerns. Existing methods of performing private third-party inference, such as Secure…

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…

Public intelligent services enabled by machine learning algorithms are vulnerable to model extraction attacks that can steal confidential information of the learning models through public queries. Differential privacy (DP) has been…

Large Language Models (LLMs) demonstrate impressive capabilities across various fields, yet their increasing use raises critical security concerns. This article reviews recent literature addressing key issues in LLM security, with a focus…

Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a central server without exchanging their private data.…

The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently learn and retain sensitive information and harmful content…

With the rapid development of artificial intelligence, large language models (LLMs) have made remarkable advancements in natural language processing. These models are trained on vast datasets to exhibit powerful language understanding and…

Safety and scalability are two critical challenges faced by practical Multi-Agent Systems (MAS). However, existing Multi-Agent Reinforcement Learning (MARL) algorithms that rely solely on reward shaping are ineffective in ensuring safety,…

RGB camera-based surveillance systems enable human action recognition for public safety and healthcare, yet raise serious privacy concerns. Existing methods rely on post-capture algorithms, which fail to protect privacy during data…

Machine learning (ML) models trained by differentially private stochastic gradient descent (DP-SGD) have much lower utility than the non-private ones. To mitigate this degradation, we propose a DP Laplacian smoothing SGD (DP-LSSGD) to train…

This study investigates privacy leakage in dimensionality reduction methods through a novel machine learning-based reconstruction attack. Employing an informed adversary threat model, we develop a neural network capable of reconstructing…

While defenses for structured PII are mature, Large Language Models (LLMs) pose a new threat: Semantic Sensitive Information (SemSI), where models infer sensitive identity attributes, generate reputation-harmful content, or hallucinate…

Machine Learning (ML), addresses a multitude of complex issues in multiple disciplines, including social sciences, finance, and medical research. ML models require substantial computing power and are only as powerful as the data utilized.…

Large language model (LLM)-powered agents are increasingly used in recommender systems (RSs) to achieve personalized behavior modeling, where the memory mechanism plays a pivotal role in enabling the agents to autonomously explore, learn…

LLM-based Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in solving complex tasks. Central to MAS is the communication topology which governs how agents exchange information internally. Consequently, the security of…