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 251–275 of 1808 papers

Title	Date	Tasks	Status	Hype
Sparse Adversarial Attack to Object Detection	Dec 26, 2020	Adversarial AttackObject	CodeCode Available	1
Sparse Adversarial Attack via Perturbation Factorization	Aug 1, 2020	Adversarial Attack	CodeCode Available	1
SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain	Mar 4, 2021	Adversarial Attack	CodeCode Available	1
Square Attack: a query-efficient black-box adversarial attack via random search	Nov 29, 2019	Adversarial Attack	CodeCode Available	1
R&R: Metric-guided Adversarial Sentence Generation	Apr 17, 2021	Adversarial AttackGeneral Classification	CodeCode Available	1
A Survey On Universal Adversarial Attack	Mar 2, 2021	Adversarial AttackSurvey	CodeCode Available	1
AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models	Jul 24, 2023	Adversarial AttackAdversarial Defense	CodeCode Available	1
Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial Attack	Oct 6, 2021	Adversarial AttackFace Swapping	CodeCode Available	1
High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks	May 28, 2019	Adversarial AttackVocal Bursts Intensity Prediction	CodeCode Available	1
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework	May 24, 2025	Adversarial AttackSpeech Tokenization	CodeCode Available	1
A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space	Dec 2, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available	1
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models	Oct 23, 2023	Adversarial AttackBlocking	CodeCode Available	1
Attacking Video Recognition Models with Bullet-Screen Comments	Oct 29, 2021	Adversarial AttackAdversarial Attack on Video Classification	CodeCode Available	1
AdvDrop: Adversarial Attack to DNNs by Dropping Information	Aug 20, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available	1
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label	Jul 1, 2022	Adversarial AttackBackdoor Attack	CodeCode Available	1
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Predictions	May 1, 2022	Adversarial AttackCombinatorial Optimization	CodeCode Available	1
Benchmarking Adversarial Robustness on Image Classification	Jun 1, 2020	Adversarial AttackAdversarial Robustness	CodeCode Available	1
BERT-ATTACK: Adversarial Attack Against BERT Using BERT	Apr 21, 2020	Adversarial Attack	CodeCode Available	1
Black-box Adversarial Example Generation with Normalizing Flows	Jul 6, 2020	Adversarial Attack	CodeCode Available	1
Boosting Adversarial Transferability via Gradient Relevance Attack	Jan 1, 2023	Adversarial Attack	CodeCode Available	1
Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework	Oct 28, 2021	Adversarial AttackLanguage Modelling	CodeCode Available	1
CARBEN: Composite Adversarial Robustness Benchmark	Jul 16, 2022	Adversarial AttackAdversarial Robustness	CodeCode Available	1
To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models	Feb 16, 2025	Adversarial AttackBackdoor Attack	CodeCode Available	1
Certifying LLM Safety against Adversarial Prompting	Sep 6, 2023	Adversarial AttackLanguage Modelling	CodeCode Available	1
Deep Variational Information Bottleneck	Dec 1, 2016	Adversarial Attack	CodeCode Available	1

Show:10 25 50

← PrevPage 11 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