Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)
-
Updated
Mar 1, 2022 - Python
Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)
“SURE: SUrvey REcipes for building reliable and robust deep networks” (CVPR 2024) & (ECCV 2024 OOD-CV Challenge Winner)
Digitally disintegrating music
cofi — corruption finder. Designed to find data corruption on storage as the data is being written
Adversarial Attacks and Defenses via Image perturbations
An analysis of yearly stock performance in a given year using VBA scripting and automation buttons and message boxes.
Effective and Robust Adversarial Training Against Data and Label Corruptions
This project quantifies the geometric and structural "break-point" of LLM representations under data corruption. Using Intrinsic Dimension and CKA mapping, it identifies the exact transformer layers where noise destroys semantic alignment and triggers Uncertainty Calibration collapse.
[ISCIT 2025] aOPIT: Robust Sparse Subspace Tracking from Corrupted Data Observations
This application securely performs deletion by overwriting image files with random data, making them unrecoverable. It’s ideal for safely deleting non-sensitive files.
Node-based glitch art application for building image processing pipelines
Add a description, image, and links to the data-corruption topic page so that developers can more easily learn about it.
To associate your repository with the data-corruption topic, visit your repo's landing page and select "manage topics."