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, a...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.展开更多
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 meas...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.展开更多
Channel prediction is an effective approach for reducing the feedback or estimation overhead in massive multi-input multi-output (m-MIMO) systems. However, existing channel prediction methods lack precision due to mod...Channel prediction is an effective approach for reducing the feedback or estimation overhead in massive multi-input multi-output (m-MIMO) systems. However, existing channel prediction methods lack precision due to model mismatch errors or network generalization issues. Large language models (LLMs) have demonstrated powerful modeling and generalization abilities, and have been successfully applied to cross-modal tasks, including the time series analysis. Leveraging the expressive power of LLMs, we propose a pre-trained LLM-empowered channel prediction(LLM4CP)method to predict the future downlink channel state information (CSI) sequence based on the historical uplink CSI sequence. We fine-tune the network while freezing most of the parameters of the pre-trained LLM for better cross-modality knowledge transfer. To bridge the gap between the channel data and the feature space of the LLM,preprocessor, embedding, and output modules are specifically tailored by taking into account unique channel characteristics. Simulations validate that the proposed method achieves state-of-the-art (SOTA) prediction performance on full-sample, few-shot, and generalization tests with low training and inference costs.展开更多
提出并实现了一个本地轻量化课程教学智能辅助系统.该系统利用IPEX-LLM(Intel PyTorch extention for large language model)加速库,在计算资源受限的设备上高效部署并运行经过QLoRA(quantum-logic optimized resource allocation)框架...提出并实现了一个本地轻量化课程教学智能辅助系统.该系统利用IPEX-LLM(Intel PyTorch extention for large language model)加速库,在计算资源受限的设备上高效部署并运行经过QLoRA(quantum-logic optimized resource allocation)框架微调的大语言模型,并结合增强检索技术,实现了智能问答、智能出题、教学大纲生成、教学演示文档生成等4个主要功能模块的课程灵活定制,在帮助教师提高教学备课和授课的质量与效率、保护数据隐私的同时,支撑学生个性化学习并提供实时反馈.在性能实验中,以集成优化后的Chatglm3-6B模型为例,该系统处理64-token输出任务时仅需4.08 s,验证了其在资源受限环境下快速推理的能力.在实践案例分析中,通过与原生Chatgml-6B和ChatGPT4.0在功能实现上的对比,进一步表明了该系统具备优越的准确性和实用性.展开更多
This paper introduces a novel multi-tiered defense architecture to protect language models from adversarial prompt attacks. We construct adversarial prompts using strategies like role emulation and manipulative assist...This paper introduces a novel multi-tiered defense architecture to protect language models from adversarial prompt attacks. We construct adversarial prompts using strategies like role emulation and manipulative assistance to simulate real threats. We introduce a comprehensive, multi-tiered defense framework named GUARDIAN (Guardrails for Upholding Ethics in Language Models) comprising a system prompt filter, pre-processing filter leveraging a toxic classifier and ethical prompt generator, and pre-display filter using the model itself for output screening. Extensive testing on Meta’s Llama-2 model demonstrates the capability to block 100% of attack prompts. The approach also auto-suggests safer prompt alternatives, thereby bolstering language model security. Quantitatively evaluated defense layers and an ethical substitution mechanism represent key innovations to counter sophisticated attacks. The integrated methodology not only fortifies smaller LLMs against emerging cyber threats but also guides the broader application of LLMs in a secure and ethical manner.展开更多
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 awaren...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.展开更多
由于社交媒体平台上所发布的非结构化信息存在数据不一致、重要程度不同等问题,使自动准确抽取所需信息并标注受灾级别成为一个有挑战性的工作。因此,结合形式概念分析(FCA)、词共现关系和上下文语义信息构建了水灾事件知识体系。利用...由于社交媒体平台上所发布的非结构化信息存在数据不一致、重要程度不同等问题,使自动准确抽取所需信息并标注受灾级别成为一个有挑战性的工作。因此,结合形式概念分析(FCA)、词共现关系和上下文语义信息构建了水灾事件知识体系。利用所构建的知识体系,基于TencentPretrain框架对大规模语言预训练模型(LLM)进行指令微调,构建了ChatFlowFlood信息抽取模型,可以在少量人工标记情况下,准确自动抽取被困情况、紧缺物资等信息;在信息抽取模型的基础上,通过模糊层次分析法(FAHP)和CRITIC法(CRiteria Importance Through Intercriteria Correlation)主客观结合评定求助信息的救援优先级,帮助决策者理解灾情紧急程度。实验结果表明,在中文社交媒体数据上,与ChatFlow-7B模型相比,ChatFlowFlood模型的FBERT指标提升了73.09%。展开更多
在过去20年中,语言建模(Language models,LM)已经成为一种主要方法,用于语言理解和生成,同时作为自然语言处理(Natural language processing,NLP)领域下游的关键技术受到广泛关注.近年来,大语言模型(Large language models,LLMs),例如Ch...在过去20年中,语言建模(Language models,LM)已经成为一种主要方法,用于语言理解和生成,同时作为自然语言处理(Natural language processing,NLP)领域下游的关键技术受到广泛关注.近年来,大语言模型(Large language models,LLMs),例如ChatGPT等技术,取得了显著进展,对人工智能乃至其他领域的变革和发展产生了深远的影响.鉴于LLMs迅猛的发展,本文首先对LLMs相关技术架构和模型规模等方面的演进历程进行了全面综述,总结了模型训练方法、优化技术以及评估手段.随后,分析了LLMs在教育、医疗、金融、工业等领域的应用现状,同时讨论了它们的优势和局限性.此外,还探讨了大语言模型针对社会伦理、隐私和安全等方面引发的安全性与一致性问题及技术措施.最后,展望了大语言模型未来的研究趋势,包括模型的规模与效能、多模态处理、社会影响等方面的发展方向.本文通过全面分析当前研究状况和未来走向,旨在为研究者提供关于大语言模型的深刻见解和启发,以推动该领域的进一步发展.展开更多
文摘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.
文摘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.
基金supported in part by the National Natural Science Foundation of China under Grants 62125101 and 62341101in part by the New Cornerstone Science Foundation through the XPLORER PRIZE+2 种基金in part by Guangdong Provincial Key Lab of Integrated Communication,Sensing and Computation for Ubiquitous Internet of Things under Grant 2023B1212010007in part by Guangzhou Municipal Science and Technology Project under Grant 2023A03J0011in part by Guangdong Provincial Department of Education Major Research Project under Grant 2023ZDZX1037.
文摘Channel prediction is an effective approach for reducing the feedback or estimation overhead in massive multi-input multi-output (m-MIMO) systems. However, existing channel prediction methods lack precision due to model mismatch errors or network generalization issues. Large language models (LLMs) have demonstrated powerful modeling and generalization abilities, and have been successfully applied to cross-modal tasks, including the time series analysis. Leveraging the expressive power of LLMs, we propose a pre-trained LLM-empowered channel prediction(LLM4CP)method to predict the future downlink channel state information (CSI) sequence based on the historical uplink CSI sequence. We fine-tune the network while freezing most of the parameters of the pre-trained LLM for better cross-modality knowledge transfer. To bridge the gap between the channel data and the feature space of the LLM,preprocessor, embedding, and output modules are specifically tailored by taking into account unique channel characteristics. Simulations validate that the proposed method achieves state-of-the-art (SOTA) prediction performance on full-sample, few-shot, and generalization tests with low training and inference costs.
文摘提出并实现了一个本地轻量化课程教学智能辅助系统.该系统利用IPEX-LLM(Intel PyTorch extention for large language model)加速库,在计算资源受限的设备上高效部署并运行经过QLoRA(quantum-logic optimized resource allocation)框架微调的大语言模型,并结合增强检索技术,实现了智能问答、智能出题、教学大纲生成、教学演示文档生成等4个主要功能模块的课程灵活定制,在帮助教师提高教学备课和授课的质量与效率、保护数据隐私的同时,支撑学生个性化学习并提供实时反馈.在性能实验中,以集成优化后的Chatglm3-6B模型为例,该系统处理64-token输出任务时仅需4.08 s,验证了其在资源受限环境下快速推理的能力.在实践案例分析中,通过与原生Chatgml-6B和ChatGPT4.0在功能实现上的对比,进一步表明了该系统具备优越的准确性和实用性.
文摘This paper introduces a novel multi-tiered defense architecture to protect language models from adversarial prompt attacks. We construct adversarial prompts using strategies like role emulation and manipulative assistance to simulate real threats. We introduce a comprehensive, multi-tiered defense framework named GUARDIAN (Guardrails for Upholding Ethics in Language Models) comprising a system prompt filter, pre-processing filter leveraging a toxic classifier and ethical prompt generator, and pre-display filter using the model itself for output screening. Extensive testing on Meta’s Llama-2 model demonstrates the capability to block 100% of attack prompts. The approach also auto-suggests safer prompt alternatives, thereby bolstering language model security. Quantitatively evaluated defense layers and an ethical substitution mechanism represent key innovations to counter sophisticated attacks. The integrated methodology not only fortifies smaller LLMs against emerging cyber threats but also guides the broader application of LLMs in a secure and ethical manner.
基金supported partly by the National Science Foundation award FMitF-2319242.
文摘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.
文摘由于社交媒体平台上所发布的非结构化信息存在数据不一致、重要程度不同等问题,使自动准确抽取所需信息并标注受灾级别成为一个有挑战性的工作。因此,结合形式概念分析(FCA)、词共现关系和上下文语义信息构建了水灾事件知识体系。利用所构建的知识体系,基于TencentPretrain框架对大规模语言预训练模型(LLM)进行指令微调,构建了ChatFlowFlood信息抽取模型,可以在少量人工标记情况下,准确自动抽取被困情况、紧缺物资等信息;在信息抽取模型的基础上,通过模糊层次分析法(FAHP)和CRITIC法(CRiteria Importance Through Intercriteria Correlation)主客观结合评定求助信息的救援优先级,帮助决策者理解灾情紧急程度。实验结果表明,在中文社交媒体数据上,与ChatFlow-7B模型相比,ChatFlowFlood模型的FBERT指标提升了73.09%。
文摘在过去20年中,语言建模(Language models,LM)已经成为一种主要方法,用于语言理解和生成,同时作为自然语言处理(Natural language processing,NLP)领域下游的关键技术受到广泛关注.近年来,大语言模型(Large language models,LLMs),例如ChatGPT等技术,取得了显著进展,对人工智能乃至其他领域的变革和发展产生了深远的影响.鉴于LLMs迅猛的发展,本文首先对LLMs相关技术架构和模型规模等方面的演进历程进行了全面综述,总结了模型训练方法、优化技术以及评估手段.随后,分析了LLMs在教育、医疗、金融、工业等领域的应用现状,同时讨论了它们的优势和局限性.此外,还探讨了大语言模型针对社会伦理、隐私和安全等方面引发的安全性与一致性问题及技术措施.最后,展望了大语言模型未来的研究趋势,包括模型的规模与效能、多模态处理、社会影响等方面的发展方向.本文通过全面分析当前研究状况和未来走向,旨在为研究者提供关于大语言模型的深刻见解和启发,以推动该领域的进一步发展.