unknownhl

CODA

We propose a novel adversarial example generation technique (i.e., CODA) for testing deep code models. Its key idea is to use code differences between the target input and reference inputs to guide the generation of adversarial examples.

Adversarial-example-paper

automated-interpretability

deep-learning-uncertainty

Literature survey, paper reviews, experimental setups and a collection of implementations for baselines methods for predictive uncertainty estimation in deep learning models.

feature-entropy

Feature entropy gives the quantification of importance degree of individual units in CNNs

neuralcollapse

Code reproducing Neural Collapse phenomenon on MSE and cross-entropy loss

NSGen

POT

POT : Python Optimal Transport

Testing-Zoo

unknownhl/Adversarial-example-paper

unknownhl/automated-interpretability

unknownhl/deep-learning-uncertainty

Literature survey, paper reviews, experimental setups and a collection of implementations for baselines methods for predictive uncertainty estimation in deep learning models.

unknownhl/feature-entropy

Feature entropy gives the quantification of importance degree of individual units in CNNs

unknownhl/neuralcollapse

Code reproducing Neural Collapse phenomenon on MSE and cross-entropy loss

unknownhl/NSGen

unknownhl/POT

POT : Python Optimal Transport

unknownhl/Testing-Zoo