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

A CNN implementation using only numpy. Supports multidimensional images, stride, etc.

Deep metric learning methods implemented in Chainer

Fre-GAN: Adversarial Frequency-consistent Audio Synthesis

Towards Interpretable Deep Metric Learning with Structural Matching

The implementation our EMNLP 2021 paper "Enhanced Language Representation with Label Knowledge for Span Extraction".

Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding (AAAI 2020) - PyTorch Implementation

The official implementation of paper Siamese Transformer Pyramid Networks for Real-Time UAV Tracking, accepted by WACV22

Aiming at the common training datsets split, spectrum preprocessing, wavelength select and calibration models algorithm involved in the spectral analysis process

Square Root Bundle Adjustment for Large-Scale Reconstruction

MoCap-Solver: A Neural Solver for Optical Motion Capture Data

CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images

Keras implementation of Normalizer-Free Networks and SGD - Adaptive Gradient Clipping

Code for the paper "Curriculum Dropout", ICCV 2017

Joint Detection and Identification Feature Learning for Person Search

discovering subdomains, hidden paths, extracting unique links

Code for CVPR 2018 paper --- Texture Mapping for 3D Reconstruction with RGB-D Sensor

CROSS-LINGUAL ABILITY OF MULTILINGUAL BERT: AN EMPIRICAL STUDY

This repo is about to create the Streamlit application for given ML model.

Source code of D-HAN: Dynamic News Recommendation with Hierarchical Attention Network

CLIPort: What and Where Pathways for Robotic Manipulation