Data-Free Model Extraction
Truong, Jean-Baptiste, Maini, Pratyush, Walls, Robert J., Papernot, Nicolas
Published in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01.06.2021)
Published in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01.06.2021)
Get full text
Conference Proceeding
Understanding Hallucinations in Diffusion Models through Mode Interpolation
Aithal, Sumukh K, Maini, Pratyush, Lipton, Zachary C, Kolter, J. Zico
Year of Publication 13.06.2024
Year of Publication 13.06.2024
Get full text
Journal Article
Rethinking LLM Memorization through the Lens of Adversarial Compression
Schwarzschild, Avi, Feng, Zhili, Maini, Pratyush, Lipton, Zachary C, Kolter, J. Zico
Year of Publication 23.04.2024
Year of Publication 23.04.2024
Get full text
Journal Article
Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
Goyal, Sachin, Maini, Pratyush, Lipton, Zachary C, Raghunathan, Aditi, Kolter, J. Zico
Year of Publication 10.04.2024
Year of Publication 10.04.2024
Get full text
Journal Article
Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling
Maini, Pratyush, Seto, Skyler, Bai, He, Grangier, David, Zhang, Yizhe, Jaitly, Navdeep
Year of Publication 29.01.2024
Year of Publication 29.01.2024
Get full text
Journal Article
TOFU: A Task of Fictitious Unlearning for LLMs
Maini, Pratyush, Feng, Zhili, Schwarzschild, Avi, Lipton, Zachary C, Kolter, J. Zico
Year of Publication 11.01.2024
Year of Publication 11.01.2024
Get full text
Journal Article
Can Neural Network Memorization Be Localized?
Maini, Pratyush, Mozer, Michael C, Sedghi, Hanie, Lipton, Zachary C, Kolter, J. Zico, Zhang, Chiyuan
Year of Publication 18.07.2023
Year of Publication 18.07.2023
Get full text
Journal Article
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
Maini, Pratyush, Goyal, Sachin, Lipton, Zachary C, Kolter, J. Zico, Raghunathan, Aditi
Year of Publication 06.07.2023
Year of Publication 06.07.2023
Get full text
Journal Article
Model-tuning Via Prompts Makes NLP Models Adversarially Robust
Raman, Mrigank, Maini, Pratyush, Kolter, J. Zico, Lipton, Zachary C, Pruthi, Danish
Year of Publication 13.03.2023
Year of Publication 13.03.2023
Get full text
Journal Article
Data-Free Model Extraction
Truong, Jean-Baptiste, Maini, Pratyush, Walls, Robert J, Papernot, Nicolas
Year of Publication 30.11.2020
Year of Publication 30.11.2020
Get full text
Journal Article
LLM Dataset Inference: Did you train on my dataset?
Maini, Pratyush, Jia, Hengrui, Papernot, Nicolas, Dziedzic, Adam
Published in arXiv.org (10.06.2024)
Get full text
Published in arXiv.org (10.06.2024)
Paper