Aounon Kumar

~Aounon_Kumar1

5

论文总数

2.5

年均投稿

4.9

平均评分

接收情况2/5

会议分布

ICLR

4

COLM

1

发表论文 (5 篇)

20251 篇

Weak-to-Strong Trustworthiness: Eliciting Trustworthiness with Weak Supervision

ICLR 2025Rejected

20244 篇

Certifying LLM Safety against Adversarial Prompting

ICLR 2024Rejected

Certifying LLM Safety against Adversarial Prompting

COLM 2024Poster

Can AI-Generated Text be Reliably Detected?

ICLR 2024Rejected

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

ICLR 2024Poster

合作者 (14)

Soheil Feizi4 篇

Himabindu Lakkaraju3 篇

Aaron Jiaxun Li2 篇

Chirag Agarwal2 篇

Suraj Srinivas2 篇

Vinu Sankar Sadasivan2 篇

Wenxiao Wang2 篇

Atoosa Chegini1 篇