热点
"红队测试" 相关文章
A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management
少点错误 2025-03-13T18:37:21.000000Z
攻破AI最强守卫，赏金2万刀！Anthropic新方法可阻止95% Claude「越狱」行为
新智元 2025-02-20T16:28:23.000000Z
攻破AI最强守卫，赏金2万刀！Anthropic新方法可阻止95% Claude「越狱」行为
智源社区 2025-02-18T05:07:22.000000Z
Scale AI Research Introduces J2 Attackers: Leveraging Human Expertise to Transform Advanced LLMs into Effective Red Teamers
MarkTechPost@AI 2025-02-17T20:19:10.000000Z
红队必看：生成式AI安全的八大实战教训
互联网安全内参 2025-02-13T11:53:16.000000Z
微软：100款 GenAI 产品安全测试背后的 8 条教训与 5 个案例总结！
PaperAgent 2025-01-28T16:13:02.000000Z
Dr. Peter Garraghan, CEO, CTO & Co-Founder at Mindgard – Interview Series
Unite.AI 2024-12-30T17:31:28.000000Z
British university spinoff Mindgard protects companies from AI threats
TechCrunch News 2024-12-20T08:07:24.000000Z
首个被人类骗钱骗感情的 AI 出现了，一段话转走几十万，马斯克点赞
APPSO 2024-12-14T05:14:56.000000Z
Best-of-N Jailbreaking: A Multi-Modal AI Approach to Identifying Vulnerabilities in Large Language Models
MarkTechPost@AI 2024-12-13T12:02:41.000000Z
速递｜AI界的恋爱赏金大赛！让AI机器人爱上你就能赚钱
Z Potentials 2024-12-07T07:46:24.000000Z
How OpenAI stress-tests its large language models
MIT Technology Review » Artificial Intelligence 2024-11-26T06:17:23.000000Z
OpenAI enhances AI safety with new red teaming methods
AI News 2024-11-22T15:47:15.000000Z
Promptfoo: An AI Tool For Testing, Evaluating and Red-Teaming LLM apps
MarkTechPost@AI 2024-11-02T07:20:35.000000Z
14款被严重低估的安全红队测试工具推荐
CISO洞察 2024-10-21T15:23:43.000000Z
日本发布《人工智能红队测试方法指南》1.0
决策研究 2024-10-10T02:24:05.000000Z
用“自动化红队测试”解决AI越狱问题，Haize Labs创业7个月估值一亿美元
36kr 2024-09-11T10:34:05.000000Z
大型语言模型（LLM）的红队测试
qz安全情报分析 2024-09-11T03:38:26.000000Z
GPT-4o模仿人类声音，诡异尖叫引OpenAI研究员恐慌！32页技术报告出炉
智源社区 2024-08-10T15:52:37.000000Z
This AI Paper from UC Berkeley Research Highlights How Task Decomposition Breaks the Safety of Artificial Intelligence (AI) Systems, Leading to Misuse
MarkTechPost@AI 2024-06-29T13:31:48.000000Z