Dayong Ye
YOU?
Author Swipe
View article: The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies
The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies Open
Inspired by the rapid development of Large Language Models (LLMs), LLM agents have evolved to perform complex tasks. LLM agents are now extensively applied across various domains, handling vast amounts of data to interact with humans and e…
View article: Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey
Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey Open
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 …
View article: Federated Unlearning With Reinforcement Learning: Adaptive Privacy Preservation for Clients
Federated Unlearning With Reinforcement Learning: Adaptive Privacy Preservation for Clients Open
View article: Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems
Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems Open
Multi-agent systems powered by Large Language Models (LLM-MAS) have demonstrated remarkable capabilities in collaborative problem-solving. However, their deployment also introduces new security risks. Existing research on LLM-based agents …
View article: Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning
Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning Open
Duplication is a prevalent issue within datasets. Existing research has demonstrated that the presence of duplicated data in training datasets can significantly influence both model performance and data privacy. However, the impact of data…
View article: Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI
Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI Open
Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While existi…
View article: Defending Against Neural Network Model Inversion Attacks via Data Poisoning
Defending Against Neural Network Model Inversion Attacks via Data Poisoning Open
Model inversion attacks pose a significant privacy threat to machine learning models by reconstructing sensitive data from their outputs. While various defenses have been proposed to counteract these attacks, they often come at the cost of…
View article: When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?
When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge? Open
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 du…
View article: Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey
Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey Open
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 …
View article: Federated TrustChain: Blockchain-Enhanced LLM Training and Unlearning
Federated TrustChain: Blockchain-Enhanced LLM Training and Unlearning Open
The development of Large Language Models (LLMs) faces a significant challenge: the exhausting of publicly available fresh data. This is because training a LLM needs a large demanding of new data. Federated learning emerges as a promising s…
View article: Reinforcement Unlearning
Reinforcement Unlearning Open
Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners. However, one important area that has been largely overlooked in the resea…
View article: Multi-Agent Reinforcement Learning for Online Food Delivery with Location Privacy Preservation
Multi-Agent Reinforcement Learning for Online Food Delivery with Location Privacy Preservation Open
Online food delivery services today are considered an essential service that gets significant attention worldwide. Many companies and individuals are involved in this field as it offers good income and numerous jobs to the community. In th…
View article: Boosting Model Inversion Attacks with Adversarial Examples
Boosting Model Inversion Attacks with Adversarial Examples Open
Model inversion attacks involve reconstructing the training data of a target model, which raises serious privacy concerns for machine learning models. However, these attacks, especially learning-based methods, are likely to suffer from low…
View article: New Challenges in Reinforcement Learning: A Survey of Security and Privacy
New Challenges in Reinforcement Learning: A Survey of Security and Privacy Open
Reinforcement learning (RL) is one of the most important branches of AI. Due to its capacity for self-adaption and decision-making in dynamic environments, reinforcement learning has been widely applied in multiple areas, such as healthcar…
View article: One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy
One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacy Open
Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a dataset or even reconstr…
View article: Model Inversion Attack against Transfer Learning: Inverting a Model without Accessing It
Model Inversion Attack against Transfer Learning: Inverting a Model without Accessing It Open
Transfer learning is an important approach that produces pre-trained teacher models which can be used to quickly build specialized student models. However, recent research on transfer learning has found that it is vulnerable to various att…
View article: Label-only Model Inversion Attack: The Attack that Requires the Least Information
Label-only Model Inversion Attack: The Attack that Requires the Least Information Open
In a model inversion attack, an adversary attempts to reconstruct the data records, used to train a target model, using only the model's output. In launching a contemporary model inversion attack, the strategies discussed are generally bas…
View article: Time-optimal and privacy preserving route planning for carpool policy
Time-optimal and privacy preserving route planning for carpool policy Open
To alleviate the traffic congestion caused by the sharp increase in the number of private cars and save commuting costs, taxi carpooling service has become the choice of many people. Current research on taxi carpooling services has focused…
View article: DP-Image: Differential Privacy for Image Data in Feature Space
DP-Image: Differential Privacy for Image Data in Feature Space Open
The excessive use of images in social networks, government databases, and industrial applications has posed great privacy risks and raised serious concerns from the public. Even though differential privacy (DP) is a widely accepted criteri…
View article: Differential Advising in Multi-Agent Reinforcement Learning
Differential Advising in Multi-Agent Reinforcement Learning Open
Agent advising is one of the main approaches to improve agent learning performance by enabling agents to share advice. Existing advising methods have a common limitation that an adviser agent can offer advice to an advisee agent only if th…
View article: Differentially Private Multi-Agent Planning for Logistic-like Problems
Differentially Private Multi-Agent Planning for Logistic-like Problems Open
Planning is one of the main approaches used to improve agents' working efficiency by making plans beforehand. However, during planning, agents face the risk of having their private information leaked. This paper proposes a novel strong pri…
View article: A Differentially Private Game Theoretic Approach for Deceiving Cyber Adversaries
A Differentially Private Game Theoretic Approach for Deceiving Cyber Adversaries Open
Cyber deception is one of the key approaches used to mislead attackers by hiding or providing inaccurate system information. There are two main factors limiting the real-world application of existing cyber deception approaches. The first l…
View article: Service Selection With QoS Correlations in Distributed Service-Based Systems
Service Selection With QoS Correlations in Distributed Service-Based Systems Open
Service selection is an important research problem in distributed service-based systems, which aims to select proper services to meet user requirements. A number of service selection approaches have been proposed in recent years. Most of t…
View article: A Survey of Self-Organization Mechanisms in Multiagent Systems
A Survey of Self-Organization Mechanisms in Multiagent Systems Open
This paper surveys the literature over the last decades in the field of self-organizing multiagent systems. Self-organization has been extensively studied and applied in multiagent systems and other fields, e.g., sensor networks and grid s…
View article: A Multi-Agent Framework for Packet Routing in Wireless Sensor Networks
A Multi-Agent Framework for Packet Routing in Wireless Sensor Networks Open
Wireless sensor networks (WSNs) have been widely investigated in recent years. One of the fundamental issues in WSNs is packet routing, because in many application domains, packets have to be routed from source nodes to destination nodes a…