Kamalika Chaudhuri
~Kamalika_Chaudhuri1
19
论文总数
9.5
年均投稿
平均评分
接收情况10/19
会议分布
ICLR
10
NeurIPS
7
ICML
2
发表论文 (19 篇)
202510 篇
5
Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations
ICLR 2025Rejected
5
Influence-based Attributions can be Manipulated
ICLR 2025Rejected
4
Can We Infer Confidential Properties of Training Data from LLMs?
NeurIPS 2025Spotlight
4
Auditing $f$-Differential Privacy in One Run
ICLR 2025Rejected
4
Auditing $f$-differential privacy in one run
ICML 2025Oral
4
Robust Locally Differentially Private Graph Analysis
ICLR 2025Rejected
3
Evaluating Deep Unlearning in Large Language Models
ICLR 2025Rejected
4
Rethinking the Role of Verbatim Memorization in LLM Privacy
NeurIPS 2025Poster
5
ExpProof : Operationalizing Explanations for Confidential Models with ZKPs
ICML 2025Poster
4
Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
NeurIPS 2025Poster
20249 篇
4
On Differentially Private U Statistics
NeurIPS 2024Poster
4
Unified Uncertainty Estimation
ICLR 2024Rejected
4
Distribution Learning with Valid Outputs Beyond the Worst-Case
NeurIPS 2024Poster
4
Déjà Vu Memorization in Vision–Language Models
NeurIPS 2024Poster
4
Large-Scale Public Data Improves Differentially Private Image Generation Quality
ICLR 2024Rejected
3
ViP: A Differentially Private Foundation Model for Computer Vision
ICLR 2024Rejected
4
Effective pruning of web-scale datasets based on complexity of concept clusters
ICLR 2024Poster
3
Measuring Dejavu Memorization Efficiently
NeurIPS 2024Poster
4
Differentially Private Vision-Language Foundation Models via Image Captioning
ICLR 2024Rejected