基本信息
浏览量:236
职业迁徙
个人简介
My research focuses on enhancing the security/privacy/robustness of ML, improving large language models, and the intersection of these topics. Some of my recent work includes:
Memorization & Privacy We've shown that LMs and diffusion models can memorize their training data, raising questions regarding privacy, copyright, GDPR statutes, and more.
Prompting & Decoding We've done some of the early work on prompting LMs, including prompt design, parameter efficiency, and understanding failure modes.
Robustness We've studied natural and adversarial distribution shifts, and we have traced model errors back to quality and diversity issues in the training data.
New Threat Models We've explored and refined new types of adversarial vulnerabilities, including stealing models weights and poisoning training sets.
Memorization & Privacy We've shown that LMs and diffusion models can memorize their training data, raising questions regarding privacy, copyright, GDPR statutes, and more.
Prompting & Decoding We've done some of the early work on prompting LMs, including prompt design, parameter efficiency, and understanding failure modes.
Robustness We've studied natural and adversarial distribution shifts, and we have traced model errors back to quality and diversity issues in the training data.
New Threat Models We've explored and refined new types of adversarial vulnerabilities, including stealing models weights and poisoning training sets.
研究兴趣
论文共 55 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
CoRR (2024)
引用0浏览0EI引用
0
0
arxiv(2024)
引用0浏览0引用
0
0
arxiv(2024)
引用0浏览0引用
0
0
Arnav Gudibande,Eric Wallace,Charlie Victor Snell,Xinyang Geng,Hao Liu, Pieter Abbeel,Sergey Levine,Dawn Song
ICLR 2024 (2024)
引用0浏览0引用
0
0
Nicholas Carlini,Daniel Paleka,Krishnamurthy Dj Dvijotham,Thomas Steinke, Jonathan Hayase,A. Feder Cooper,Katherine Lee,Matthew Jagielski,Milad Nasr, Arthur Conmy,Eric Wallace, David Rolnick,
arxiv(2024)
引用0浏览0引用
0
0
CoRR (2023): 35413-35425
引用42浏览0EI引用
42
0
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn