Evaluating Privacy Leakage and Memorization Attacks on Large Language Models (LLMs) in Generative AI Applications

The recent interest in the deployment of Generative AI applications that use large language models (LLMs) has brought to the forefront significant privacy concerns, notably the leakage of Personally Identifiable Information (PII) and other confidential or protected information that may have been memorized during training, specifically during a fine-tuning or customization process. We describe different black-box attacks from potential adversaries and study their impact on the amount and type of information that may be recovered from commonly used and deployed LLMs. Our research investigates the relationship between PII leakage, memorization, and factors such as model size, architecture, and the nature of attacks employed. The study utilizes two broad categories of attacks: PII leakage-focused attacks (auto-completion and extraction attacks) and memorization-focused attacks (various membership inference attacks). The findings from these investigations are quantified using an array of evaluative metrics, providing a detailed understanding of LLM vulnerabilities and the effectiveness of different attacks.

Security Vulnerability Analyses of Large Language Models (LLMs) through Extension of the Common Vulnerability Scoring System (CVSS) Framework

Large Language Models (LLMs) have revolutionized Generative Artificial Intelligence (GenAI) tasks, becoming an integral part of various applications in society, including text generation, translation, summarization, and more. However, their widespread usage emphasizes the critical need to enhance their security posture to ensure the integrity and reliability of their outputs and minimize harmful effects. Prompt injections and training data poisoning attacks are two of the most prominent vulnerabilities in LLMs, which could potentially lead to unpredictable and undesirable behaviors, such as biased outputs, misinformation propagation, and even malicious content generation. The Common Vulnerability Scoring System (CVSS) framework provides a standardized approach to capturing the principal characteristics of vulnerabilities, facilitating a deeper understanding of their severity within the security and AI communities. By extending the current CVSS framework, we generate scores for these vulnerabilities such that organizations can prioritize mitigation efforts, allocate resources effectively, and implement targeted security measures to defend against potential risks.

Evolution and Prospects of Foundation Models: From Large Language Models to Large Multimodal Models

Since the 1950s,when the Turing Test was introduced,there has been notable progress in machine language intelligence.Language modeling,crucial for AI development,has evolved from statistical to neural models over the last two decades.Recently,transformer-based Pre-trained Language Models(PLM)have excelled in Natural Language Processing(NLP)tasks by leveraging large-scale training corpora.Increasing the scale of these models enhances performance significantly,introducing abilities like context learning that smaller models lack.The advancement in Large Language Models,exemplified by the development of ChatGPT,has made significant impacts both academically and industrially,capturing widespread societal interest.This survey provides an overview of the development and prospects from Large Language Models(LLM)to Large Multimodal Models(LMM).It first discusses the contributions and technological advancements of LLMs in the field of natural language processing,especially in text generation and language understanding.Then,it turns to the discussion of LMMs,which integrates various data modalities such as text,images,and sound,demonstrating advanced capabilities in understanding and generating cross-modal content,paving new pathways for the adaptability and flexibility of AI systems.Finally,the survey highlights the prospects of LMMs in terms of technological development and application potential,while also pointing out challenges in data integration,cross-modal understanding accuracy,providing a comprehensive perspective on the latest developments in this field.

Construction and preliminary application of large language model for reservoir performance analysis

A large language model(LLM)is constructed to address the sophisticated demands of data retrieval and analysis,detailed well profiling,computation of key technical indicators,and the solutions to complex problems in reservoir performance analysis(RPA).The LLM is constructed for RPA scenarios with incremental pre-training,fine-tuning,and functional subsystems coupling.Functional subsystem and efficient coupling methods are proposed based on named entity recognition(NER),tool invocation,and Text-to-SQL construction,all aimed at resolving pivotal challenges in developing the specific application of LLMs for RDA.This study conducted a detailed accuracy test on feature extraction models,tool classification models,data retrieval models and analysis recommendation models.The results indicate that these models have demonstrated good performance in various key aspects of reservoir dynamic analysis.The research takes some injection and production well groups in the PK3 Block of the Daqing Oilfield as an example for testing.Testing results show that our model has significant potential and practical value in assisting reservoir engineers with RDA.The research results provide a powerful support to the application of LLM in reservoir performance analysis.

DeBERTa-GRU: Sentiment Analysis for Large Language Model

Modern technological advancements have made social media an essential component of daily life.Social media allow individuals to share thoughts,emotions,and ideas.Sentiment analysis plays the function of evaluating whether the sentiment of the text is positive,negative,neutral,or any other personal emotion to understand the sentiment context of the text.Sentiment analysis is essential in business and society because it impacts strategic decision-making.Sentiment analysis involves challenges due to lexical variation,an unlabeled dataset,and text distance correlations.The execution time increases due to the sequential processing of the sequence models.However,the calculation times for the Transformer models are reduced because of the parallel processing.This study uses a hybrid deep learning strategy to combine the strengths of the Transformer and Sequence models while ignoring their limitations.In particular,the proposed model integrates the Decoding-enhanced with Bidirectional Encoder Representations from Transformers(BERT)attention(DeBERTa)and the Gated Recurrent Unit(GRU)for sentiment analysis.Using the Decoding-enhanced BERT technique,the words are mapped into a compact,semantic word embedding space,and the Gated Recurrent Unit model can capture the distance contextual semantics correctly.The proposed hybrid model achieves F1-scores of 97%on the Twitter Large Language Model(LLM)dataset,which is much higher than the performance of new techniques.

Enhancing Relational Triple Extraction in Specific Domains:Semantic Enhancement and Synergy of Large Language Models and Small Pre-Trained Language Models

In the process of constructing domain-specific knowledge graphs,the task of relational triple extraction plays a critical role in transforming unstructured text into structured information.Existing relational triple extraction models facemultiple challenges when processing domain-specific data,including insufficient utilization of semantic interaction information between entities and relations,difficulties in handling challenging samples,and the scarcity of domain-specific datasets.To address these issues,our study introduces three innovative components:Relation semantic enhancement,data augmentation,and a voting strategy,all designed to significantly improve the model’s performance in tackling domain-specific relational triple extraction tasks.We first propose an innovative attention interaction module.This method significantly enhances the semantic interaction capabilities between entities and relations by integrating semantic information fromrelation labels.Second,we propose a voting strategy that effectively combines the strengths of large languagemodels(LLMs)and fine-tuned small pre-trained language models(SLMs)to reevaluate challenging samples,thereby improving the model’s adaptability in specific domains.Additionally,we explore the use of LLMs for data augmentation,aiming to generate domain-specific datasets to alleviate the scarcity of domain data.Experiments conducted on three domain-specific datasets demonstrate that our model outperforms existing comparative models in several aspects,with F1 scores exceeding the State of the Art models by 2%,1.6%,and 0.6%,respectively,validating the effectiveness and generalizability of our approach.

A large language model-powered literature review for high-angle annular dark field imaging

High-angle annular dark field(HAADF)imaging in scanning transmission electron microscopy(STEM)has become an indispensable tool in materials science due to its ability to offer sub-°A resolution and provide chemical information through Z-contrast.This study leverages large language models(LLMs)to conduct a comprehensive bibliometric analysis of a large amount of HAADF-related literature(more than 41000 papers).By using LLMs,specifically ChatGPT,we were able to extract detailed information on applications,sample preparation methods,instruments used,and study conclusions.The findings highlight the capability of LLMs to provide a new perspective into HAADF imaging,underscoring its increasingly important role in materials science.Moreover,the rich information extracted from these publications can be harnessed to develop AI models that enhance the automation and intelligence of electron microscopes.

LKPNR: Large Language Models and Knowledge Graph for Personalized News Recommendation Framework

Accurately recommending candidate news to users is a basic challenge of personalized news recommendation systems.Traditional methods are usually difficult to learn and acquire complex semantic information in news texts,resulting in unsatisfactory recommendation results.Besides,these traditional methods are more friendly to active users with rich historical behaviors.However,they can not effectively solve the long tail problem of inactive users.To address these issues,this research presents a novel general framework that combines Large Language Models(LLM)and Knowledge Graphs(KG)into traditional methods.To learn the contextual information of news text,we use LLMs’powerful text understanding ability to generate news representations with rich semantic information,and then,the generated news representations are used to enhance the news encoding in traditional methods.In addition,multi-hops relationship of news entities is mined and the structural information of news is encoded using KG,thus alleviating the challenge of long-tail distribution.Experimental results demonstrate that compared with various traditional models,on evaluation indicators such as AUC,MRR,nDCG@5 and nDCG@10,the framework significantly improves the recommendation performance.The successful integration of LLM and KG in our framework has established a feasible way for achieving more accurate personalized news recommendation.Our code is available at https://github.com/Xuan-ZW/LKPNR.

Large language models in laparoscopic surgery: A transformative opportunity

This opinion paper explores the transformative potential of large language models(LLMs)in laparoscopic surgery and argues for their integration to enhance surgical education,decision support,reporting,and patient care.LLMs can revolutionize surgical education by providing personalized learning experiences and accelerating skill acquisition.Intelligent decision support systems powered by LLMs can assist surgeons in making complex decisions,optimizing surgical workflows,and improving patient outcomes.Moreover,LLMs can automate surgical reporting and generate personalized patient education materials,streamlining documentation and improving patient engagement.However,challenges such as data scarcity,surgical semantic capture,real-time inference,and integration with existing systems need to be addressed for successful LLM integration.The future of laparoscopic surgery lies in the seamless integration of LLMs,enabling autonomous robotic surgery,predictive surgical planning,intraoperative decision support,virtual surgical assistants,and continuous learning.By harnessing the power of LLMs,laparoscopic surgery can be transformed,empowering surgeons and ultimately benefiting patients.

Evaluating the role of large language models in inflammatory bowel disease patient information

This letter evaluates the article by Gravina et al on ChatGPT’s potential in providing medical information for inflammatory bowel disease patients.While promising,it highlights the need for advanced techniques like reasoning+action and retrieval-augmented generation to improve accuracy and reliability.Emphasizing that simple question and answer testing is insufficient,it calls for more nuanced evaluation methods to truly gauge large language models’capabilities in clinical applications.

Potential use of large language models for mitigating students’problematic social media use:ChatGPT as an example

The problematic use of social media has numerous negative impacts on individuals'daily lives,interpersonal relationships,physical and mental health,and more.Currently,there are few methods and tools to alleviate problematic social media,and their potential is yet to be fully realized.Emerging large language models(LLMs)are becoming increasingly popular for providing information and assistance to people and are being applied in many aspects of life.In mitigating problematic social media use,LLMs such as ChatGPT can play a positive role by serving as conversational partners and outlets for users,providing personalized information and resources,monitoring and intervening in problematic social media use,and more.In this process,we should recognize both the enormous potential and endless possibilities of LLMs such as ChatGPT,leveraging their advantages to better address problematic social media use,while also acknowledging the limitations and potential pitfalls of ChatGPT technology,such as errors,limitations in issue resolution,privacy and security concerns,and potential overreliance.When we leverage the advantages of LLMs to address issues in social media usage,we must adopt a cautious and ethical approach,being vigilant of the potential adverse effects that LLMs may have in addressing problematic social media use to better harness technology to serve individuals and society.

Large Language Model Based Semantic Parsing for Intelligent Database Query Engine

With the rapid development of artificial intelligence, large language models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. These models have great potential to enhance database query systems, enabling more intuitive and semantic query mechanisms. Our model leverages LLM’s deep learning architecture to interpret and process natural language queries and translate them into accurate database queries. The system integrates an LLM-powered semantic parser that translates user input into structured queries that can be understood by the database management system. First, the user query is pre-processed, the text is normalized, and the ambiguity is removed. This is followed by semantic parsing, where the LLM interprets the pre-processed text and identifies key entities and relationships. This is followed by query generation, which converts the parsed information into a structured query format and tailors it to the target database schema. Finally, there is query execution and feedback, where the resulting query is executed on the database and the results are returned to the user. The system also provides feedback mechanisms to improve and optimize future query interpretations. By using advanced LLMs for model implementation and fine-tuning on diverse datasets, the experimental results show that the proposed method significantly improves the accuracy and usability of database queries, making data retrieval easy for users without specialized knowledge.

Storyline Extraction of Document-Level Events Using Large Language Models

This article proposes a document-level prompt learning approach using LLMs to extract the timeline-based storyline. Through verification tests on datasets such as ESCv1.2 and Timeline17, the results show that the prompt + one-shot learning proposed in this article works well. Meanwhile, our research findings indicate that although timeline-based storyline extraction has shown promising prospects in the practical applications of LLMs, it is still a complex natural language processing task that requires further research.

The Auxiliary Role of Large Language Models in Clinical Dialogues

In recent years,large language models(LLMs)have made significant progress in natural language processing(NLP).These models not only perform well in a variety of language tasks but also show great potential in the medical field.This paper aims to explore the application of LLMs in clinical dialogues,analyzing their role in improving the efficiency of doctor-patient communication,aiding in diagnosis and treatment,and providing emotional support.The paper also discusses the challenges and limitations of the model in terms of privacy protection,ethical issues,and practical applications.Through comprehensive analysis,we conclude that applying LLMs in clinical dialogues is promising.However,it requires careful consideration and caution by practitioners in practice.

Research status and application of artificial intelligence large models in the oil and gas industry

This article elucidates the concept of large model technology,summarizes the research status of large model technology both domestically and internationally,provides an overview of the application status of large models in vertical industries,outlines the challenges and issues confronted in applying large models in the oil and gas sector,and offers prospects for the application of large models in the oil and gas industry.The existing large models can be briefly divided into three categories:large language models,visual large models,and multimodal large models.The application of large models in the oil and gas industry is still in its infancy.Based on open-source large language models,some oil and gas enterprises have released large language model products using methods like fine-tuning and retrieval augmented generation.Scholars have attempted to develop scenario-specific models for oil and gas operations by using visual/multimodal foundation models.A few researchers have constructed pre-trained foundation models for seismic data processing and interpretation,as well as core analysis.The application of large models in the oil and gas industry faces challenges such as current data quantity and quality being difficult to support the training of large models,high research and development costs,and poor algorithm autonomy and control.The application of large models should be guided by the needs of oil and gas business,taking the application of large models as an opportunity to improve data lifecycle management,enhance data governance capabilities,promote the construction of computing power,strengthen the construction of“artificial intelligence+energy”composite teams,and boost the autonomy and control of large model technology.

Smaller & Smarter: Score-Driven Network Chaining of Smaller Language Models

With the continuous evolution and expanding applications of Large Language Models (LLMs), there has been a noticeable surge in the size of the emerging models. It is not solely the growth in model size, primarily measured by the number of parameters, but also the subsequent escalation in computational demands, hardware and software prerequisites for training, all culminating in a substantial financial investment as well. In this paper, we present novel techniques like supervision, parallelization, and scoring functions to get better results out of chains of smaller language models, rather than relying solely on scaling up model size. Firstly, we propose an approach to quantify the performance of a Smaller Language Models (SLM) by introducing a corresponding supervisor model that incrementally corrects the encountered errors. Secondly, we propose an approach to utilize two smaller language models (in a network) performing the same task and retrieving the best relevant output from the two, ensuring peak performance for a specific task. Experimental evaluations establish the quantitative accuracy improvements on financial reasoning and arithmetic calculation tasks from utilizing techniques like supervisor models (in a network of model scenario), threshold scoring and parallel processing over a baseline study.

Large language models in health care:Development,applications,and challenges

Recently,the emergence of ChatGPT,an artificial intelligence chatbot developed by OpenAI,has attracted significant attention due to its exceptional language comprehension and content generation capabilities,highlighting the immense potential of large language models(LLMs).LLMs have become a burgeoning hotspot across many fields,including health care.Within health care,LLMs may be classified into LLMs for the biomedical domain and LLMs for the clinical domain based on the corpora used for pre-training.In the last 3 years,these domain-specific LLMs have demonstrated exceptional perform-ance on multiple natural language processing tasks,surpassing the perform-ance of general LLMs as well.This not only emphasizes the significance of developing dedicated LLMs for the specific domains,but also raises expectations for their applications in health care.We believe that LLMs may be used widely in preconsultation,diagnosis,and management,with appropriate development and supervision.Additionally,LLMs hold tremen-dous promise in assisting with medical education,medical writing and other related applications.Likewise,health care systems must recognize and address the challenges posed by LLMs.

基于人工智能LLM技术的虚拟患者系统构建与临床教学应用

目的构建一种基于人工智能大语言模型(large language model,LLM)技术、可用于医学教育的新型虚拟患者(virtual patient,VP)系统,评价该系统在基层医生进修学习全科医学临床思维中的应用效果。方法选取2021年1月至2024年2月在东南大学附属中大医院进修的基层社区医生为研究对象,随机分为试验组和对照组,分别采用基于LLM的VP系统教学、传统教学方法进行授课,通过临床思维理论知识考核、临床思维能力考核、课程满意度调查评估教学效果,并对结果进行相应的统计学分析。结果共纳入124名基层社区医生,其中试验组60例、对照组64例,两组在一般基线资料上差异无统计学意义,具有可比性。课程结束后,试验组临床思维理论知识考核成绩显著高于对照组(83.83±3.15 vs.79.92±4.52,P<0.01),且不及格率显著低于对照组(0.00%vs.9.38%,P<0.05);试验组在临床思维能力3个维度(批判性、系统性、循证思维)方面教学后分数均显著高于教学前,而对照组仅在批判性思维维度上教学前后差异有统计学意义;教学后试验组在系统思维、循证思维方面分数均显著高于对照组(P<0.05),但在批判性思维上两组分数差异无统计学意义。试验组对授课的总体满意度也显著高于对照组(93.33%vs.85.48%,P<0.05)。结论基于LLM的VP系统提升了学员对临床思维理论知识的掌握程度,也促进了其临床思维能力的培养,该教学方法可为其他医学教育群体提供新的教学工具和思路。

ChatModeler:基于大语言模型的人机协作迭代式需求获取和建模方法

需求获取和建模是需求工程中的关键步骤,影响后续系统设计与实现.传统的需求获取和建模方法通常由需求提供者、需求分析师等多类干系人共同协作、反复迭代完成,需要耗费大量的人力.如何减轻需求提供者与需求分析师的负担、提高获取和建模的效率有着重要意义.现有工作中有的使用知识库来提供更多知识,以辅助获取或者建模,有的利用自然语言处理等技术对获取或者建模过程进行自动化,但是它们并没有减轻需求提供者的负担.利用大语言模型(large language models,LLMs)的生成能力,提供了一种人机协作的迭代式需求获取和建模框架ChatModeler.具体来说,根据真实世界中需求团队的分工及协作关系,将部分需求提供者、需求分析师等角色的工作由大语言模型承担,而需求提供者只需要进行确认.为大语言模型扮演的各种角色进行了提示词设计,该提示词会随需求的元模型而变化.ChatModeler在7个需求案例上与3种需求模型的自动建模方法进行了14组对比实验,证明了ChatModeler在降低需求提供者的负担和生成高质量需求模型2个方面上的优越性.

A survey on large language model(LLM)security and privacy:The Good,The Bad,and The Ugly

Large Language Models(LLMs),such as ChatGPT and Bard,have revolutionized natural language understanding and generation.They possess deep language comprehension,human-like text generation capabilities,contextual awareness,and robust problem-solving skills,making them invaluable in various domains(e.g.,search engines,customer support,translation).In the meantime,LLMs have also gained traction in the security community,revealing security vulnerabilities and showcasing their potential in security-related tasks.This paper explores the intersection of LLMs with security and privacy.Specifically,we investigate how LLMs positively impact security and privacy,potential risks and threats associated with their use,and inherent vulnerabilities within LLMs.Through a comprehensive literature review,the paper categorizes the papers into‘‘The Good’’(beneficial LLM applications),‘‘The Bad’’(offensive applications),and‘‘The Ugly’’(vulnerabilities of LLMs and their defenses).We have some interesting findings.For example,LLMs have proven to enhance code security(code vulnerability detection)and data privacy(data confidentiality protection),outperforming traditional methods.However,they can also be harnessed for various attacks(particularly user-level attacks)due to their human-like reasoning abilities.We have identified areas that require further research efforts.For example,Research on model and parameter extraction attacks is limited and often theoretical,hindered by LLM parameter scale and confidentiality.Safe instruction tuning,a recent development,requires more exploration.We hope that our work can shed light on the LLMs’potential to both bolster and jeopardize cybersecurity.