Adversarial Defense

176 papers with code • 10 benchmarks • 5 datasets

Competitions with currently unpublished results:

Libraries

Use these libraries to find Adversarial Defense models and implementations

A Simple and Yet Fairly Effective Defense for Graph Neural Networks

sennadir/noisygnn 21 Feb 2024

Successful combinations of our NoisyGNN approach with existing defense techniques demonstrate even further improved adversarial defense results.

1
21 Feb 2024

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

chs20/robustvlm 19 Feb 2024

The CLIP model, or one of its variants, is used as a frozen vision encoder in many vision-language models (VLMs), e. g. LLaVA and OpenFlamingo.

40
19 Feb 2024

Detection and Defense of Unlearnable Examples

hala64/udp 14 Dec 2023

Detectability of unlearnable examples with simple networks motivates us to design a novel defense method.

0
14 Dec 2023

Robust MRI Reconstruction by Smoothed Unrolling (SMUG)

sjames40/smug_journal 12 Dec 2023

To address this problem, we propose a novel image reconstruction framework, termed Smoothed Unrolling (SMUG), which advances a deep unrolling-based MRI reconstruction model using a randomized smoothing (RS)-based robust learning approach.

0
12 Dec 2023

Defense Against Adversarial Attacks using Convolutional Auto-Encoders

Shreyasi2002/Adversarial_Attack_Defense 6 Dec 2023

Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures.

2
06 Dec 2023

Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization

callous-youth/last 19 Oct 2023

Adversarial Training (AT), pivotal in fortifying the robustness of deep learning models, is extensively adopted in practical applications.

0
19 Oct 2023

Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria

changzhang777/ancra 5 Oct 2023

Deep neural networks are vulnerable to adversarial noise.

3
05 Oct 2023

DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training

OPTML-Group/DeepZero 3 Oct 2023

Our extensive experiments show that DeepZero achieves state-of-the-art (SOTA) accuracy on ResNet-20 trained on CIFAR-10, approaching FO training performance for the first time.

21
03 Oct 2023

Language Guided Adversarial Purification

Visual-Conception-Group/LGAP 19 Sep 2023

Adversarial purification using generative models demonstrates strong adversarial defense performance.

2
19 Sep 2023

Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification

sjames40/adversarial-purification-for-mri 11 Sep 2023

In particular, we present a robustification strategy that improves the resilience of DL-based MRI reconstruction methods by utilizing pretrained diffusion models as noise purifiers.

2
11 Sep 2023