Dynamic graph data mining has gained popularity in recent years due to the rich information contained in dynamic graphs and their widespread use in the real world. Despite the advances in dynamic graph neural networks...
详细信息
In recent years, depression, as a serious mental illness, has received widespread attention from various sectors of society. How to identify depressive emotions in a timely manner and detect depression has become an u...
详细信息
Lightweight containers in serverless-based vehicular edge computing (SVEC) offer flexible service provisioning for edge service providers (ESPs), enabling quick response to various service requests from mobile vehicle...
详细信息
Recently, retrieval-augmented generation(RAG) systems have attracted attention for addressing issues like hallucinations and reliance on outdated knowledge in large language models(LLMs). Privacy studies have revealed...
详细信息
Recently, retrieval-augmented generation(RAG) systems have attracted attention for addressing issues like hallucinations and reliance on outdated knowledge in large language models(LLMs). Privacy studies have revealed that RAG systems are vulnerable to membership leakage in determining whether a specific target sample is included in the RAG knowledge base. Existing membership inference attack(MIA) methods for RAGs primarily rely on similarity scores between the system's responses and the true answers. These methods assume that a higher similarity score indicates the sample is more likely to have been used by the RAG system to enhance its response, suggesting it is a member of the knowledge ***, this study uncovers an important insight: the similarity metric does not directly represent the membership status,instead measures the response difficulty of the sample. To address this, we propose a novel membership inference attack for RAG systems, called difficulty-calibrated membership inference attack(DC-MIA). It first classifies high-similarity samples as members, and then calibrates the membership scores of samples with comparable raw similarity scores using a likelihood ratio test. Experimental results demonstrate that our approach significantly improves the performance of membership inference attacks on RAG systems.
Large language models signify a pivotal advancement in general artificial intelligence, exhibiting capabilities that exceed human performance in diverse tasks. Nevertheless, these models often lack expertise in specia...
详细信息
In recent years, microservice architectures have benefited from low coupling and high cohesion characteristics, allowing flexible on-demand deployment of complex applications and simplifying the difficulty of developi...
详细信息
Code summarization aims to generate natural language (NL) summaries automatically given the source code snippet, which aids developers in understanding source code faster and improves software maintenance. Recent appr...
详细信息
Extensive simulation sample data are crucial for the intelligent interpretation of synthetic aperture radar (SAR) data of the lunar surface using deep learning techniques. Existing simulation methods inadequately capt...
详细信息
To minimize the propagation of redundant data in wireless sensor networks, conserve energy, and extend network lifespan, we propose an algorithm (R-IEHOBP) that combines radial clustering and an elephant swarm neural ...
详细信息
In recent years, with the increasingly severe traffic environment, most cities are facing various traffic congestion problems, and the demand for intelligent regulation of traffic signals is also increasing. In this s...
详细信息
暂无评论