Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks

Last update: Dec 12, 2022

Related tags

Deep Learning SODEF

Overview

Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks

Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attackss.

Qiyu Kang, Yang Song, Qinxu Ding, Wee Peng Tay

Environment settings

OS: Ubuntu 18.04
GPU: RTX 2080 Ti, RTX a5000, RTX 3090
Cuda: 11.1 or 10.2
Python: >=3.6
PyTorch: >= 1.6.0
Torchvision: >= 0.7.0

Empirical Evaluations

Compatibility of SODEF

In this section, we show compatibility of SODEF using TRADES:

We append our SODEF after TRADES net to improve the model robustness against adversarial attacks. TRADES works as the feature extractor $h_{\boldsymbol{\phi}}$ as in our paper. Please note TRADES weights are kept fixed during the training. We use the pretrained model provided by TRADES Repo.

Attack / Model	TRADES ℒ_∞	TRADES+SODEF ℒ_∞	TRADES ℒ₂	TRADES+SODEF ℒ₂
Clean	85.48	85.18	85.48	85.18
APGD_CE	56.08	70.90	61.74	74.35
APGD_DLR^T	53.70	64.15	59.22	68.55
FAB^T	54.18	82.92	60.31	83.15
Square	59.12	62.21	72.65	76.02
AutoAttack	53.69	57.76	59.42	67.75

Tab 1. Classification accuracy (%) using TRADES (w/ and w/o SODEF) under AutoAttack on adversarial CIFAR10 examples with ℒ₂ norm (ϵ = 0.5) and ℒ_∞ norm (ϵ = 8/255).

Transfer attack:

Classification accuracy for adv examples generated from original pretrained model using AA ℒ_∞ (ϵ = 8/255) attacks : 61.94%.

cd trades_r
python sodef_eval_ode.py

cd trades_r
sodef_eval_transfer.ipynb

Notification

More test code and models will be uploaded soon after packing.

We currenly only upload the test code for SODEF. Please understand we have strict protocols for code release as this research is partially funded by corporate funding. We will upload the training code as soon as permission is granted.

Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks

Related tags

Overview

Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks

Environment settings

Empirical Evaluations

Compatibility of SODEF

In this section, we show compatibility of SODEF using TRADES:

Notification

Owner

Kang Qiyu

Multiple-Object Tracking with Transformer

Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models (ICCV 2021 Oral)

A demo of how to use JAX to create a simple gravity simulation

Processed, version controlled history of Minecraft's generated data and assets

PyTorch implementation of ''Background Activation Suppression for Weakly Supervised Object Localization''.

A new video text spotting framework with Transformer

Library for time-series-forecasting-as-a-service.

Training code and evaluation benchmarks for the "Self-Supervised Policy Adaptation during Deployment" paper.

Simulation of Self Driving Car

BT-Unet: A-Self-supervised-learning-framework-for-biomedical-image-segmentation-using-Barlow-Twins

A PyTorch implementation of the paper Mixup: Beyond Empirical Risk Minimization in PyTorch

We present a regularized self-labeling approach to improve the generalization and robustness properties of fine-tuning.

Generates all variables from your .tf files into a variables.tf file.

Delving into Localization Errors for Monocular 3D Object Detection, CVPR'2021

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

Code for the paper: Sketch Your Own GAN

Compute FID scores with PyTorch.

MAME is a multi-purpose emulation framework.

auto-tuning momentum SGD optimizer