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	Hype
Adversarial Attacks and Defences for Skin Cancer Classification	Dec 13, 2022	Adversarial AttackAdversarial Defense	—Unverified	0
Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection	Dec 13, 2022	Active LearningAdversarial Attack	—Unverified	0
HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Design	Dec 12, 2022	Adversarial Attack	CodeCode Available	1
General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignments	Dec 11, 2022	Adversarial AttackAdversarial Defense	—Unverified	0
Understanding and Combating Robust Overfitting via Input Loss Landscape Analysis and Regularization	Dec 9, 2022	Adversarial Attack	CodeCode Available	0
Targeted Adversarial Attacks against Neural Network Trajectory Predictors	Dec 8, 2022	Adversarial AttackTrajectory Forecasting	—Unverified	0
Pareto Regret Analyses in Multi-objective Multi-armed Bandit	Dec 1, 2022	Adversarial Attack	—Unverified	0
AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification	Nov 29, 2022	Adversarial AttackClassification	—Unverified	0
Data Poisoning Attack Aiming the Vulnerability of Continual Learning	Nov 29, 2022	Adversarial AttackContinual Learning	—Unverified	0
Imperceptible Adversarial Attack via Invertible Neural Networks	Nov 28, 2022	Adversarial Attack	CodeCode Available	1
Foiling Explanations in Deep Neural Networks	Nov 27, 2022	Adversarial AttackExplainable artificial intelligence	CodeCode Available	0
SAGA: Spectral Adversarial Geometric Attack on 3D Meshes	Nov 24, 2022	Adversarial Attack	CodeCode Available	1
Explainable and Safe Reinforcement Learning for Autonomous Air Mobility	Nov 24, 2022	Adversarial AttackDeep Reinforcement Learning	CodeCode Available	0
Benchmarking Adversarially Robust Quantum Machine Learning at Scale	Nov 23, 2022	Adversarial AttackAdversarial Attack Detection	—Unverified	0
PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples	Nov 22, 2022	Adversarial AttackPoint Cloud Classification	—Unverified	0
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack	Nov 21, 2022	Activity RecognitionAdversarial Attack	CodeCode Available	1
Ignore Previous Prompt: Attack Techniques For Language Models	Nov 17, 2022	Adversarial AttackAdversarial Text	CodeCode Available	2
T-SEA: Transfer-based Self-Ensemble Attack on Object Detection	Nov 16, 2022	Adversarial AttackModel Optimization	CodeCode Available	1
Person Text-Image Matching via Text-Feature Interpretability Embedding and External Attack Node Implantation	Nov 16, 2022	Adversarial AttackDiversity	CodeCode Available	0
Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation	Nov 15, 2022	Adversarial Attack	—Unverified	0
MORA: Improving Ensemble Robustness Evaluation with Model-Reweighing Attack	Nov 15, 2022	Adversarial Attack	CodeCode Available	1
Universal Distributional Decision-based Black-box Adversarial Attack with Reinforcement Learning	Nov 15, 2022	Adversarial Attackreinforcement-learning	—Unverified	0
Generating Textual Adversaries with Minimal Perturbation	Nov 12, 2022	Adversarial Attack	CodeCode Available	0
Robust Smart Home Face Recognition under Starving Federated Data	Nov 10, 2022	Adversarial AttackFace Recognition	CodeCode Available	0
Preserving Semantics in Textual Adversarial Attacks	Nov 8, 2022	Adversarial AttackSentence	CodeCode Available	1

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