ChatGPT安全威胁研究

被引:15
作者
朱孟垚
李兴华
机构
[1] 西安电子科技大学网络与信息安全学院
关键词
ChatGPT; 大型语言模型; 人工智能安全; 数据安全; 隐私保护;
D O I
暂无
中图分类号
TP309 [安全保密]; TP18 [人工智能理论];
学科分类号
081201 ; 0839 ; 1402 ; 081104 ; 0812 ; 0835 ; 1405 ;
摘要
随着深度学习技术与自然语言处理技术的快速发展,以ChatGPT为代表的大型语言模型应运而生,然而其在诸多领域展现出令人惊讶的能力的同时,也暴露出诸多安全威胁,这引发了学术界与产业界的担忧.首先,介绍了ChatGPT及其系列模型的发展历程、工作模式与训练方式;然后,从用户和模型2个层面总结并分析了当前ChatGPT可能遇到的各类安全问题,并提出应对思路与方案;最后,对ChatGPT以及大型语言模型领域未来如何安全可信地发展进行了展望.
引用
收藏
页码:533 / 542
页数:10
相关论文
共 12 条
  • [1] Do ChatGPT and Other AI Chatbots Pose a Cybersecurity Risk?: An Exploratory Study.[J].Sebastian Glorin.International Journal of Security and Privacy in Pervasive Computing (IJSPPC).2023, 1
  • [2] ChatGPT Utility in Healthcare Education; Research; and Practice: Systematic Review on the Promising Perspectives and Valid Concerns.[J].Sallam Malik.Healthcare.2023, 6
  • [3] Welcome to the Era of ChatGPT et al..[J].Teubner Timm;Flath Christoph M.;Weinhardt Christof;van der Aalst Wil;Hinz Oliver.Business & Information Systems Engineering.2023, 2
  • [4] Assessing the Value of ChatGPT for Clinical Decision Support Optimization..[J].Liu Siru;Wright Aileen P;Patterson Barron L;Wanderer Jonathan P;Turer Robert W;Nelson Scott D;McCoy Allison B;Sittig Dean F;Wright Adam.medRxiv : the preprint server for health sciences.2023,
  • [5] Automatic Extraction of Medication Mentions from Tweets-Overview of the BioCreative VII Shared Task 3 Competition..[J].Weissenbacher Davy;O'Connor Karen;Rawal Siddharth;Zhang Yu;Tsai Richard TzongHan;Miller Timothy;Xu Dongfang;Anderson Carol;Liu Bo;Han Qing;Zhang Jinfeng;Kulev Igor;K?prü Berkay;RodriguezEsteban Raul;Ozkirimli Elif;Ayach Ammer;Roller Roland;Piccolo Stephen;Han Peijin;Vydiswaran V G Vinod;Tekumalla Ramya;Banda Juan M;Bagherzadeh Parsa;Bergler Sabine;Silva Jo?o F;Almeida Tiago;Mart
  • [6] ChatGPT: five priorities for research
    Bockting, Claudi
    van Dis, Eva A. M.
    Bollen, Johan
    van Rooij, Robert
    Zuidema, Willem L.
    [J]. NATURE, 2023, 614 (7947) : 224 - 226
  • [7] ChatGPT and Other Large Language Models Are Double-edged Swords
    Shen, Yiqiu
    Heacock, Laura
    Elias, Jonathan
    Hentel, Keith D.
    Reig, Beatriu
    Shih, George
    Moy, Linda
    [J]. RADIOLOGY, 2023, 307 (02)
  • [8] A Survey on Neural Network Interpretability
    Zhang, Yu
    Tino, Peter
    Leonardis, Ales
    Tang, Ke
    [J]. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2021, 5 (05): : 726 - 742
  • [9] GPT-3: Its Nature, Scope, Limits, and Consequences
    Floridi, Luciano
    Chiriatti, Massimo
    [J]. MINDS AND MACHINES, 2020, 30 (04) : 681 - 694
  • [10] What Does ChatGPT Say:The DAO from Algorithmic Intelligence to Linguistic Intelligence.[J].Fei-Yue Wang;Qinghai Miao;Xuan Li;Xingxia Wang;Yilun Lin;.IEEE/CAA Journal of Automatica Sinica.2023, 03