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

Self-Correcting Quantum Many-Body Control using Reinforcement Learning with Tensor Networks

Convnet transfer - Code for paper How transferable are features in deep neural networks?

f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation

Audio Source Separation is the process of separating a mixture into isolated sounds from individual sources

Back to Basics: Efficient Network Compression via IMP

Exploit ILP to learn symmetry breaking constraints of ASP programs.

Large scale and asynchronous Hyperparameter Optimization at your fingertip.

Score refinement for confidence-based 3D multi-object tracking

An official implementation of the Anchor DETR.

LETR: Line Segment Detection Using Transformers without Edges

PyTorch implementation of Memory-based semantic segmentation for off-road unstructured natural environments.

The code for our NeurIPS 2021 paper "Kernelized Heterogeneous Risk Minimization".

Custom IMDB Dataset is extracted between 2020-2021 and custom distilBERT model is trained for movie success probability prediction

This is the repository of shape matching algorithm Iterative Rotations and Assignments (IRA)

Continuous Augmented Positional Embeddings (CAPE) implementation for PyTorch

Implementation of "StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis"

Data-Uncertainty Guided Multi-Phase Learning for Semi-supervised Object Detection

Learning to Map Large-scale Sparse Graphs on Memristive Crossbar

Generate images from texts. In Russian. In PaddlePaddle

[PNAS2021] The neural architecture of language: Integrative modeling converges on predictive processing