Adversarial Attack

An Adversarial Attack is a technique to find a perturbation that changes the prediction of a machine learning model. The perturbation can be very small and imperceptible to human eyes.

Source: Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 701–725 of 1808 papers

Title	Date	Tasks	Status	Score
Enhanced countering adversarial attacks via input denoising and feature restoring	Nov 19, 2021	Adversarial AttackDenoising	CodeCode Available	5
Exploiting vulnerabilities of deep neural networks for privacy protection	Jul 19, 2020	Adversarial AttackQuantization	CodeCode Available	5
Adversarial Attacks on Data Attribution	Sep 9, 2024	Adversarial AttackAdversarial Robustness	CodeCode Available	5
Explainable Graph Neural Networks Under Fire	Jun 10, 2024	Adversarial Attack	CodeCode Available	5
Excess Capacity and Backdoor Poisoning	Sep 2, 2021	Adversarial AttackBackdoor Attack	CodeCode Available	5
Combining Generators of Adversarial Malware Examples to Increase Evasion Rate	Apr 14, 2023	Adversarial Attack	CodeCode Available	5
Adversarial Images for Variational Autoencoders	Dec 1, 2016	Adversarial Attack	CodeCode Available	5
Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction	Nov 22, 2019	Adversarial Attackimage-classification	CodeCode Available	5
Enhancing Neural Models with Vulnerability via Adversarial Attack	Dec 1, 2020	Adversarial AttackSentence	CodeCode Available	5
Enhancing Real-World Adversarial Patches through 3D Modeling of Complex Target Scenes	Feb 10, 2021	Adversarial AttackInference Attack	CodeCode Available	5
Improving Sequence Modeling Ability of Recurrent Neural Networks via Sememes	Oct 20, 2019	Adversarial AttackLanguage Modeling	CodeCode Available	5
Hidden Activations Are Not Enough: A General Approach to Neural Network Predictions	Sep 20, 2024	Adversarial Attack	CodeCode Available	5
Expanding Scope: Adapting English Adversarial Attacks to Chinese	Jun 8, 2023	Adversarial AttackAdversarial Robustness	CodeCode Available	5
Query-efficient Meta Attack to Deep Neural Networks	Jun 6, 2019	Adversarial AttackMeta-Learning	CodeCode Available	5
ColorFool: Semantic Adversarial Colorization	Nov 25, 2019	Adversarial AttackColorization	CodeCode Available	5
Explainable and Safe Reinforcement Learning for Autonomous Air Mobility	Nov 24, 2022	Adversarial AttackDeep Reinforcement Learning	CodeCode Available	5
Exploring the Vulnerability of Natural Language Processing Models via Universal Adversarial Texts	Dec 1, 2021	Adversarial Attacktext-classification	CodeCode Available	5
A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees	Jul 10, 2018	Adversarial AttackAdversarial Defense	CodeCode Available	5
EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial Attacks	Jul 12, 2021	Adversarial Attack	CodeCode Available	5
A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks	Nov 27, 2018	Adversarial Attack	CodeCode Available	5
Class-Conditioned Transformation for Enhanced Robust Image Classification	Mar 27, 2023	Adversarial AttackClassification	CodeCode Available	5
EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware Detection	Oct 7, 2021	Adversarial AttackAndroid Malware Detection	CodeCode Available	5
Evaluating the Validity of Word-level Adversarial Attacks with Large Language Models	Aug 15, 2024	Adversarial AttackLanguage Modeling	CodeCode Available	5
Resilience of Named Entity Recognition Models under Adversarial Attack	Jul 1, 2022	Adversarial Attacknamed-entity-recognition	CodeCode Available	5
Exacerbating Algorithmic Bias through Fairness Attacks	Dec 16, 2020	Adversarial AttackBIG-bench Machine Learning	CodeCode Available	5

Show:10 25 50

← PrevPage 29 of 73Next →

All datasets CIFAR-10 CIFAR-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Xu et al.	Attack: PGD20	78.68	—	Unverified
2	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	78.13	—	Unverified
3	TRADES-ANCRA/ResNet18	Attack: AutoAttack	59.7	—	Unverified
4	AdvTraining [madry2018]	Attack: PGD20	48.44	—	Unverified
5	TRADES [zhang2019b]	Attack: PGD20	45.9	—	Unverified
6	XU-Net	Robust Accuracy	1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	51.28	—	Unverified
2	multi-resolution self-ensembles	Attack: AutoAttack	47.85	—	Unverified