Darshan Thaker

~Darshan_Thaker1

4

论文总数

2.0

年均投稿

4.8

平均评分

接收情况2/4

会议分布

ICLR

2

NeurIPS

2

发表论文 (4 篇)

20252 篇

KDA: A Knowledge-Distilled Attacker for Scalable LLM Red Teaming

ICLR 2025withdrawn

SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations

NeurIPS 2025Poster

20242 篇

A Linearly Convergent GAN Inversion-based Algorithm for Reverse Engineering of Deceptions

ICLR 2024Rejected

PaCE: Parsimonious Concept Engineering for Large Language Models

NeurIPS 2024Poster

合作者 (9)

Rene Vidal4 篇

Kwan Ho Ryan Chan3 篇

Buyun Liang2 篇

Liangzu Peng1 篇

Aditya Chattopadhyay1 篇

Chris Callison-Burch1 篇

Tianjiao Ding1 篇