huanranchen

I'm a research intern in TSAIL, Tsinghua University. I'm interested in Trustworthy ML, diffusion models.

Pinned Repositories

AdversarialAttacks
Language:Python61 3 42
ASRNorm
a pytorch implement of Adversarially Adaptive Normalization for Single Domain Generalization
Language:Python13 2 21
CommonWeaknessDetection
Official code implement of object detection part in "Rethinking Model Ensemble in Transfer-based Adversarial Attacks"
Language:Python8 1 11
DiffusionClassifier
Official code implement of Robust Classification via a Single Diffusion Model
Language:Python65 2 43
NICO-2022
Implement the dataloader
Language:Python4 1 00
NoisedDiffusionClassifiers
Official code implement of "Your Diffusion Model is Secretly a Certifiably Robust Classifier"
Language:Python9 2 01
RectifiedFlow
My implementation of Rectified FLow
Language:Python5 1 00
SupContrast
a pytorch implement of Supervised Contrastive Learning with memory bank(queue)
Language:Python15 1 00
Visualize-Loss-Landscape
Respect to the input tensor instead of paramters of NN
Language:Python15 1 01
VLMTransfer
A package that achieves 95%+ transfer attack success rate against GPT-4
Language:Python17 1 10

huanranchen's Repositories

huanranchen/DiffusionClassifier
Official code implement of Robust Classification via a Single Diffusion Model
Language:Python65 2 43
huanranchen/AdversarialAttacks
Language:Python61 3 42
huanranchen/VLMTransfer
A package that achieves 95%+ transfer attack success rate against GPT-4
Language:Python17 1 10
huanranchen/Visualize-Loss-Landscape
Respect to the input tensor instead of paramters of NN
Language:Python15 1 01
huanranchen/ASRNorm
a pytorch implement of Adversarially Adaptive Normalization for Single Domain Generalization
Language:Python13 2 21
huanranchen/NoisedDiffusionClassifiers
Official code implement of "Your Diffusion Model is Secretly a Certifiably Robust Classifier"
Language:Python9 2 01
huanranchen/CommonWeaknessDetection
Official code implement of object detection part in "Rethinking Model Ensemble in Transfer-based Adversarial Attacks"
Language:Python8 1 11
huanranchen/RectifiedFlow
My implementation of Rectified FLow
Language:Python5 1 00
huanranchen/NICO-2022
Implement the dataloader
Language:Python4 1 00
huanranchen/Similar-Target-Attacker
Official pytorch implement of paper "Boosting Adversarial Attack with Similar Target"
Language:Python4 3 01
huanranchen/EnergyBasedGenerativeModel
Language:Python3 1 00
huanranchen/SAF
a pytorch implement of Sharpness-Aware Training for Free
Language:Python3 1 0
huanranchen/Expression-Evaluation
Expression Evaluation in c++
Language:C++2 1 0
huanranchen/SEDD
Language:Python2
huanranchen/T3A
unofficial pytorch implement of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization
Language:Python2 1 0
huanranchen/ZeroSampleKD
Language:Python2 1 0
huanranchen/COCO-Detection-Attack
Language:Python1 1 00
huanranchen/ConvNeXt
Address the gradient vanishing in convnext
Language:Python1 1 0
huanranchen/CutMix-MixUp
a pytorch implement of cutmix, which solve some problem on original cutmix
Language:Python1 1 0
huanranchen/INRIA-Detection-Attack
Language:Python1 1 0
huanranchen/PoissonFlow
Language:Python1 1 0
huanranchen/robustbench
RobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]
Language:Python1 0 0
huanranchen/Visualization
Some visualization function that I always use
Language:Python1 1 0
huanranchen/CGIWebServer
CGI Web Server implemented by Huanran
Language:Python1 0
huanranchen/DetectionAttack
huanran detection attack research
Language:Python
huanranchen/DiffusionClassifiers
Language:SCSS1 0
huanranchen/FlowGenerativeModel
my implement of flow based generative models
Language:Python1 0
huanranchen/huanranchen.github.io
Huanran Chen's Academic Personal Homepage
Language:SCSS0 0
huanranchen/talkingface-toolkit
Language:Python0 0
huanranchen/Translation-Invariant-Attacks
The translation-invariant adversarial attack method to improve the transferability of adversarial examples.
Language:Python0 0