Code for "Diversity can be Transferred: Output Diversification for White- and Black-box Attacks"

Last update: Dec 11, 2022

Related tags

Overview

Output Diversified Sampling (ODS)

This is the github repository for the NeurIPS 2020 paper "Diversity can be Transferred: Output Diversification for White- and Black-box Attacks".

Requirement

Please install PyTorch, pickle, argparse, and numpy

Running experiments

ODS for score-based black-box attacks

The following experiments combine ODS with Simple Black-Box Attack (SimBA).

Evaluation:

The evaluation is held for 5 sample images on ImageNet (images are already resized and cropped).

# untargeted settings with ODS:
python blackbox_simbaODS.py --num_sample 5 --ODS 
# targeted settings with ODS:
python blackbox_simbaODS.py --num_sample 5 --num_step 30000 --ODS --targeted

ODS for decision-based black-box attacks

The following experiments combine ODS with Boundary Attack.

Additional Requirement

Please install Foolbox, Python>=3.6

Evaluation:

The evaluation is held for 5 sample images on ImageNet (images are already resized and cropped).

# untargeted settings with ODS:
python blackbox_boundaryODS.py --num_sample 5 --ODS 
# targeted settings with ODS:
python blackbox_boundaryODS.py --num_sample 5 --ODS --targeted
# untargeted settings with random sampling:
python blackbox_boundaryODS.py --num_sample 5 
# targeted settings with random sampling:
python blackbox_boundaryODS.py --num_sample 5 --targeted

Acknowledgement

Our codes for Boundary Attack are based on Foolbox repo.

ODS for initialization of white-box attacks (ODI)

The following experiments combine ODI with PGD attack.

Training of target model (Adversarial Training):

python whitebox_train_cifar10.py --model-dir [PATH_TO_SAVE_FOLDER] --data-dir [PATH_TO_DATA_FOLDER]

Evaluation PGD attack with ODI:

# Evaluate PGD attack with ODI:
python whitebox_pgd_attack_cifar10_ODI.py --ODI-num-steps 2 --model-path [PATH_TO_THE_MODEL] --data-dir [PATH_TO_DATA_FOLDER] 
# Evaluate PGD attack with naive random initialization (sampled from a uniform distribution):
python whitebox_pgd_attack_cifar10_ODI.py --ODI-num-steps 0 --model-path [PATH_TO_THE_MODEL] --data-dir [PATH_TO_DATA_FOLDER]

Acknowledgement

Our codes for white-box attacks are based on TRADES official repo.

Citation

If you use this code for your research, please cite our paper:

@inproceedings{tashiro2020ods,
  title={Diversity can be Transferred: Output Diversification for White- and Black-box Attacks},
  author={Tashiro, Yusuke and Song, Yang and Ermon, Stefano},
  booktitle={Advances in Neural Information Processing Systems},
  year={2020}
}

Code for "Diversity can be Transferred: Output Diversification for White- and Black-box Attacks"

Related tags

Overview

Output Diversified Sampling (ODS)

Requirement

Running experiments

ODS for score-based black-box attacks

Evaluation:

ODS for decision-based black-box attacks

Additional Requirement

Evaluation:

Acknowledgement

ODS for initialization of white-box attacks (ODI)

Training of target model (Adversarial Training):

Evaluation PGD attack with ODI:

Acknowledgement

Citation

Owner

[ECCV'20] Convolutional Occupancy Networks

Deploying PyTorch Model to Production with FastAPI in CUDA-supported Docker

N-gram models- Unsmoothed, Laplace, Deleted Interpolation

Pytorch implementation for the paper: Contrastive Learning for Cold-start Recommendation

Neural Oblivious Decision Ensembles

Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark

Official code of "Mitigating the Mutual Error Amplification for Semi-Supervised Object Detection"

Pytorch Geometric Tutorials

[CVPR 2021] Scan2Cap: Context-aware Dense Captioning in RGB-D Scans

Neuron class provides LNU (Linear Neural Unit), QNU (Quadratic Neural Unit), RBF (Radial Basis Function), MLP (Multi Layer Perceptron), MLP-ELM (Multi Layer Perceptron - Extreme Learning Machine) neurons learned with Gradient descent or LeLevenberg–Marquardt algorithm

Deep Learning & 3D Convolutional Neural Networks for Speaker Verification

PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"

Fast convergence of detr with spatially modulated co-attention

Code for Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks

Repository of continual learning papers

Implementation of Deep Deterministic Policy Gradiet Algorithm in Tensorflow

Attack classification models with transferability, black-box attack; unrestricted adversarial attacks on imagenet

PyTorch implementation of Towards Accurate Alignment in Real-time 3D Hand-Mesh Reconstruction (ICCV 2021).

The AugNet Python module contains functions for the fast computation of image similarity.

Udacity's CS101: Intro to Computer Science - Building a Search Engine