Journal of Information Security Reserach ›› 2025, Vol. 11 ›› Issue (E2): 299-.
Online:2025-12-27
Published:2025-12-29
李文瑾祝荣吉骆嘉敏高东范敦球
(绿盟科技集团股份有限公司北京100089)
通讯作者:
李文瑾
硕士.主要研究方向为攻防对抗、AI安全.
liwenjin@nsfocus.com
作者简介:李文瑾
硕士.主要研究方向为攻防对抗、AI安全.
liwenjin@nsfocus.com
祝荣吉
研究员.主要研究方向为AI应用安全、Web应用安全、云安全.
zhurongji@nsfocus.com
骆嘉敏
研究员.主要研究方向为大模型应用安全、Web应用安全.
luojiamin@nsfocus.com
高东
硕士，研究员.主要研究方向为智能攻防对抗、AI应用安全.
gaodong2@nsfocus.com
范敦球
博士.主要研究方向为聚焦高阶安全检测与防御.
fandunqiu@nsfocus.com
［1］包泽芃, 钱铁云. 大模型红队测试研究综述［J］. 计算机科学, 2025, 52(1): 3441［2］李南, 丁益东, 江浩宇, 等. 面向大语言模型的越狱攻击综述［J］. 计算机研究与发展, 2024, 61(5): 11561181［3］Shir T, Sagi T. Wiz Research finds architecture risks that may compromise AIasaService providers and consequently risk customer data; works with Hugging Face on mitigations［EBOL］. 2024 ［20250916］. https:www.wiz.ioblogwizandhuggingfaceaddressriskstoaiinfrastructure［4］新智元. 第一个被人类骗钱的AI傻了, 近5万美元不翼而飞！ Scaling Law还能带我们到AGI吗?［EBOL］. (20241130) ［20241213］. https:mp.weixin.qq.comsfKA4cO1VvvnWqSsTdsM_MA［5］秦臻, 庄添铭, 朱国淞, 等. 面向人工智能模型的安全攻击和防御策略综述［J］. 计算机研究与发展, 2024, 61(10): 26272648［6］OWASP Group. OWASP Top 10 for large language model applications［EBOL］. 2023 ［20240913］. https:owasp.orgwwwprojecttop10forlargelanguagemodelapplic |
| [1] | . Research Progress on Detection Technologies for Network Attack Based on Large Language Model#br# [J]. Journal of Information Security Reserach, 2026, 12(1): 16-. |
| [2] | . Smart Contract Vulnerabilities Based on Differential Evolutionary Algorithms and Solution Time Prediction Detection#br# [J]. Journal of Information Security Reserach, 2026, 12(1): 24-. |
| [3] | . PUFbased Identity Authentication for Internet of Things Against Machine Learning Attacks in Zerotrust Architecture#br# [J]. Journal of Information Security Reserach, 2026, 12(1): 33-. |
| [4] | . Object Removal Video Tampering Detection and Localization Based on Learnable Ptuning#br# [J]. Journal of Information Security Reserach, 2026, 12(1): 61-. |
| [5] |
.
The EU Artificial Intelligence Regulatory Sandbox System and Its Enlightenment#br#
#br#
[J]. Journal of Information Security Reserach, 2026, 12(1): 82-.
|
| [6] | . [J]. Journal of Information Security Reserach, 2025, 11(E2): 2-. |
| [7] | . [J]. Journal of Information Security Reserach, 2025, 11(E2): 8-. |
| [8] | . [J]. Journal of Information Security Reserach, 2025, 11(E2): 12-. |
| [9] | . [J]. Journal of Information Security Reserach, 2025, 11(E2): 15-. |
| [10] | . [J]. Journal of Information Security Reserach, 2025, 11(E2): 19-. |
| [11] | . [J]. Journal of Information Security Reserach, 2025, 11(E2): 25-. |
| [12] | . [J]. Journal of Information Security Reserach, 2025, 11(E2): 31-. |
| [13] | . [J]. Journal of Information Security Reserach, 2025, 11(E2): 35-. |
| [14] | . [J]. Journal of Information Security Reserach, 2025, 11(E2): 44-. |
| [15] | . [J]. Journal of Information Security Reserach, 2025, 11(E2): 48-. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||
