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

Voice Conversion Using Speech-to-Speech Neuro-Style Transfer

Code for the paper "Generative design of breakwaters usign deep convolutional neural network as a surrogate model"

Understanding Convolutional Neural Networks from Theoretical Perspective via Volterra Convolution

【CVPR 2021, Variational Inference Framework, PyTorch】 From Rain Generation to Rain Removal

My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot

Using contrastive learning and OpenAI's CLIP to find good embeddings for images with lossy transformations

A lightweight python AUTOmatic-arRAY library.

Official Implementation of "Designing an Encoder for StyleGAN Image Manipulation"

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

Multilingual Image Captioning

PyToch implementation of A Novel Self-supervised Learning Task Designed for Anomaly Segmentation

Unofficial TensorFlow implementation of the Keyword Spotting Transformer model

This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.

An OpenAI Gym environment for Super Mario Bros

GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data

"NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search".

Kinetics-Data-Preprocessing

用强化学习DQN算法，训练AI模型来玩合成大西瓜游戏，提供Keras版本和PARL（paddle）版本

Malware Bypass Research using Reinforcement Learning

QQ Browser 2021 AI Algorithm Competition Track 1 1st Place Program