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 1151–1175 of 1808 papers

Title	Date	Tasks	Status	Hype
A Perceptual Distortion Reduction Framework: Towards Generating Adversarial Examples with High Perceptual Quality and Attack Success Rate	May 1, 2021	Adversarial Attack	—Unverified	0
GasHis-Transformer: A Multi-scale Visual Transformer Approach for Gastric Histopathological Image Detection	Apr 29, 2021	Adversarial AttackGeneral Classification	—Unverified	0
AdvHaze: Adversarial Haze Attack	Apr 28, 2021	Adversarial Attack	—Unverified	0
Delving into Data: Effectively Substitute Training for Black-box Attack	Apr 26, 2021	Adversarial Attack	—Unverified	0
3D Adversarial Attacks Beyond Point Cloud	Apr 25, 2021	Adversarial Attack	CodeCode Available	1
Influence Based Defense Against Data Poisoning Attacks in Online Learning	Apr 24, 2021	Adversarial AttackData Poisoning	—Unverified	0
Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors	Apr 22, 2021	Adversarial AttackObject	CodeCode Available	0
Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting	Apr 22, 2021	Adversarial AttackAdversarial Robustness	CodeCode Available	0
Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions	Apr 22, 2021	Adversarial Attack	—Unverified	0
Robust Certification for Laplace Learning on Geometric Graphs	Apr 22, 2021	Adversarial AttackAdversarial Robustness	—Unverified	0
Staircase Sign Method for Boosting Adversarial Attacks	Apr 20, 2021	Adversarial Attack	CodeCode Available	1
Adversarial Diffusion Attacks on Graph-based Traffic Prediction Models	Apr 19, 2021	Adversarial AttackManagement	CodeCode Available	0
Best Practices for Noise-Based Augmentation to Improve the Performance of Deployable Speech-Based Emotion Recognition Systems	Apr 18, 2021	Adversarial AttackAutomatic Speech Recognition	—Unverified	0
R&R: Metric-guided Adversarial Sentence Generation	Apr 17, 2021	Adversarial AttackGeneral Classification	CodeCode Available	1
Fashion-Guided Adversarial Attack on Person Segmentation	Apr 17, 2021	Adversarial AttackHuman Instance Segmentation	CodeCode Available	0
Mitigating Adversarial Attack for Compute-in-Memory Accelerator Utilizing On-chip Finetune	Apr 13, 2021	Adversarial Attack	—Unverified	0
Distributed Estimation over Directed Graphs Resilient to Sensor Spoofing	Apr 10, 2021	Adversarial Attack	—Unverified	0
Improving Robustness of Deep Reinforcement Learning Agents: Environment Attack based on the Critic Network	Apr 7, 2021	Adversarial AttackDeep Reinforcement Learning	CodeCode Available	0
Semantically Stealthy Adversarial Attacks against Segmentation Models	Apr 5, 2021	Adversarial AttackSegmentation	—Unverified	0
Evaluating Neural Model Robustness for Machine Comprehension	Apr 1, 2021	Adversarial Attackmodel	—Unverified	0
Statistical inference for individual fairness	Mar 30, 2021	Adversarial AttackFairness	CodeCode Available	0
Robust Reinforcement Learning under model misspecification	Mar 29, 2021	Adversarial Attackmodel	CodeCode Available	0
IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking	Mar 27, 2021	Adversarial Attackimage-classification	CodeCode Available	1
Adversarial Attacks on Deep Learning Based mmWave Beam Prediction in 5G and Beyond	Mar 25, 2021	Adversarial AttackBeam Prediction	—Unverified	0
Vulnerability of Appearance-based Gaze Estimation	Mar 24, 2021	Adversarial AttackGaze Estimation	—Unverified	0

Show:10 25 50

← PrevPage 47 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