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

An end-to-end machine learning web app to predict rugby scores (Pandas, SQLite, Keras, Flask, Docker)

Code for Referring Image Segmentation via Cross-Modal Progressive Comprehension, CVPR2020.

Converts geometry node attributes to built-in attributes

Production First and Production Ready End-to-End Speech Recognition Toolkit

Hierarchical Attentive Recurrent Tracking

PyTorch code for our paper "Attention in Attention Network for Image Super-Resolution"

PyTorch ,ONNX and TensorRT implementation of YOLOv4

Tool for installing and updating MiSTer cores and other files

[ECCVW2020] Robust Long-Term Object Tracking via Improved Discriminative Model Prediction (RLT-DiMP)

Project repo for the paper SILT: Self-supervised Lighting Transfer Using Implicit Image Decomposition

MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification

PyTorch Implementation of PIXOR: Real-time 3D Object Detection from Point Clouds

Certified Patch Robustness via Smoothed Vision Transformers

The PyTorch implementation for paper "Neural Texture Extraction and Distribution for Controllable Person Image Synthesis" (CVPR2022 Oral)

Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision (ICCV 2021)

Full Transformer Framework for Robust Point Cloud Registration with Deep Information Interaction

Keras + Hyperopt: A very simple wrapper for convenient hyperparameter optimization

Proof-Of-Concept Piano-Drums Music AI Model/Implementation

Tutorials, assignments, and competitions for MIT Deep Learning related courses.

EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction