Adversarial Robustness

Adversarial Robustness evaluates the vulnerabilities of machine learning models under various types of adversarial attacks.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 776–800 of 1746 papers

Title	Date	Tasks	Status	Hype
Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization	Nov 22, 2022	Adversarial Robustness	—Unverified	0
Enhancing Accuracy and Robustness of Steering Angle Prediction with Attention Mechanism	Nov 21, 2022	Adversarial RobustnessAutonomous Driving	—Unverified	0
Towards Adversarial Robustness of Deep Vision Algorithms	Nov 19, 2022	Adversarial Robustnessimage-classification	—Unverified	0
Generalizable Deepfake Detection with Phase-Based Motion Analysis	Nov 17, 2022	Adversarial RobustnessDeepFake Detection	—Unverified	0
Improving Interpretability via Regularization of Neural Activation Sensitivity	Nov 16, 2022	Adversarial RobustnessExplanation Fidelity Evaluation	—Unverified	0
Differentially Private Optimizers Can Learn Adversarially Robust Models	Nov 16, 2022	Adversarial Robustness	—Unverified	0
Improved techniques for deterministic l2 robustness	Nov 15, 2022	Adversarial Robustness	CodeCode Available	0
Demystify Transformers & Convolutions in Modern Image Deep Networks	Nov 10, 2022	Adversarial RobustnessImage Deep Networks	CodeCode Available	1
Accelerating Adversarial Perturbation by 50% with Semi-backward Propagation	Nov 9, 2022	Adversarial Robustness	—Unverified	0
Towards Adversarially Robust Recommendation from Adaptive Fraudster Detection	Nov 8, 2022	Adversarial RobustnessRecommendation Systems	—Unverified	0
Robust Lottery Tickets for Pre-trained Language Models	Nov 6, 2022	Adversarial Robustness	CodeCode Available	1
An Adversarial Robustness Perspective on the Topology of Neural Networks	Nov 4, 2022	Adversarial Robustness	CodeCode Available	0
Improving Adversarial Robustness to Sensitivity and Invariance Attacks with Deep Metric Learning	Nov 4, 2022	Adversarial RobustnessMetric Learning	—Unverified	0
Data-free Defense of Black Box Models Against Adversarial Attacks	Nov 3, 2022	Adversarial Robustness	CodeCode Available	0
Visually Adversarial Attacks and Defenses in the Physical World: A Survey	Nov 3, 2022	Adversarial RobustnessSurvey	—Unverified	0
Verifying And Interpreting Neural Networks using Finite Automata	Nov 2, 2022	Adversarial Robustness	CodeCode Available	0
Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain	Nov 1, 2022	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks	Nov 1, 2022	Adversarial RobustnessPseudo Label	CodeCode Available	1
DensePure: Understanding Diffusion Models towards Adversarial Robustness	Nov 1, 2022	Adversarial RobustnessDenoising	—Unverified	0
Scoring Black-Box Models for Adversarial Robustness	Oct 31, 2022	Adversarial Robustness	—Unverified	0
FI-ODE: Certifiably Robust Forward Invariance in Neural ODEs	Oct 30, 2022	Adversarial Robustnesscontinuous-control	CodeCode Available	0
Improving Hyperspectral Adversarial Robustness Under Multiple Attacks	Oct 28, 2022	Adversarial RobustnessSemantic Segmentation	—Unverified	0
Towards Reliable Neural Specifications	Oct 28, 2022	Adversarial Robustness	—Unverified	0
Improving Adversarial Robustness with Self-Paced Hard-Class Pair Reweighting	Oct 26, 2022	Adversarial RobustnessModel Optimization	CodeCode Available	0
Disentangled Text Representation Learning with Information-Theoretic Perspective for Adversarial Robustness	Oct 26, 2022	Adversarial RobustnessRepresentation Learning	—Unverified	0

Show:10 25 50

← PrevPage 32 of 70Next →

All datasets AdvGLUE CIFAR-10 ImageNet ImageNet-A ImageNet-C Stylized ImageNet CIFAR-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	DeBERTa (single model)	Accuracy	0.61	—	Unverified
2	ALBERT (single model)	Accuracy	0.59	—	Unverified
3	T5 (single model)	Accuracy	0.57	—	Unverified
4	SMART_RoBERTa (single model)	Accuracy	0.54	—	Unverified
5	FreeLB (single model)	Accuracy	0.5	—	Unverified
6	RoBERTa (single model)	Accuracy	0.5	—	Unverified
7	InfoBERT (single model)	Accuracy	0.46	—	Unverified
8	ELECTRA (single model)	Accuracy	0.42	—	Unverified
9	BERT (single model)	Accuracy	0.34	—	Unverified
10	SMART_BERT (single model)	Accuracy	0.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Mixed classifier	Accuracy	95.23	—	Unverified
2	Stochastic-LWTA/PGD/WideResNet-34-10	Accuracy	92.26	—	Unverified
3	Stochastic-LWTA/PGD/WideResNet-34-5	Accuracy	91.88	—	Unverified
4	GLOT-DR	Accuracy	84.13	—	Unverified
5	TRADES-ANCRA/ResNet18	Accuracy	81.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet-50 (SGD, Cosine)	Accuracy	77.4	—	Unverified
2	ResNet-50 (SGD, Step)	Accuracy	76.9	—	Unverified
3	DeiT-S (AdamW, Cosine)	Accuracy	76.8	—	Unverified
4	ResNet-50 (AdamW, Cosine)	Accuracy	76.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DeiT-S (AdamW, Cosine)	Accuracy	12.2	—	Unverified
2	ResNet-50 (SGD, Cosine)	Accuracy	3.3	—	Unverified
3	ResNet-50 (SGD, Step)	Accuracy	3.2	—	Unverified
4	ResNet-50 (AdamW, Cosine)	Accuracy	3.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet-50 (AdamW, Cosine)	mean Corruption Error (mCE)	59.3	—	Unverified
2	ResNet-50 (SGD, Step)	mean Corruption Error (mCE)	57.9	—	Unverified
3	ResNet-50 (SGD, Cosine)	mean Corruption Error (mCE)	56.9	—	Unverified
4	DeiT-S (AdamW, Cosine)	mean Corruption Error (mCE)	48	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DeiT-S (AdamW, Cosine)	Accuracy	13	—	Unverified
2	ResNet-50 (SGD, Cosine)	Accuracy	8.4	—	Unverified
3	ResNet-50 (SGD, Step)	Accuracy	8.3	—	Unverified
4	ResNet-50 (AdamW, Cosine)	Accuracy	8.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Mixed Classifier	Clean Accuracy	85.21	—	Unverified
2	ResNet18/MART-ANCRA	Clean Accuracy	60.1	—	Unverified