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 926–950 of 1746 papers

Title	Date	Tasks	Status
A Novel Noise Injection-based Training Scheme for Better Model Robustness	Feb 17, 2023	Adversarial RobustnessComputational Efficiency	—Unverified
Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions	Feb 17, 2023	Adversarial RobustnessFairness	—Unverified
Adversarial Contrastive Distillation with Adaptive Denoising	Feb 17, 2023	Adversarial RobustnessDenoising	—Unverified
XploreNAS: Explore Adversarially Robust & Hardware-efficient Neural Architectures for Non-ideal Xbars	Feb 15, 2023	Adversarial RobustnessNeural Architecture Search	—Unverified
IB-RAR: Information Bottleneck as Regularizer for Adversarial Robustness	Feb 9, 2023	Adversarial Robustness	CodeCode Available
Robustness Implies Fairness in Causal Algorithmic Recourse	Feb 7, 2023	Adversarial RobustnessFairness	CodeCode Available
GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks	Feb 6, 2023	Adversarial RobustnessData Augmentation	CodeCode Available
Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks	Feb 6, 2023	Adversarial RobustnessImage Segmentation	—Unverified
Rethinking Robust Contrastive Learning from the Adversarial Perspective	Feb 5, 2023	Adversarial RobustnessContrastive Learning	CodeCode Available
Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense	Feb 2, 2023	Adversarial DefenseAdversarial Robustness	CodeCode Available
Hyperbolic Contrastive Learning	Feb 2, 2023	Adversarial RobustnessContrastive Learning	—Unverified
Provably Bounding Neural Network Preimages	Feb 2, 2023	Adversarial RobustnessGPU	CodeCode Available
CertViT: Certified Robustness of Pre-Trained Vision Transformers	Feb 1, 2023	Adversarial Robustness	CodeCode Available
On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex	Jan 30, 2023	Adversarial RobustnessLanguage Modeling	—Unverified
Towards Adversarial Realism and Robust Learning for IoT Intrusion Detection and Classification	Jan 30, 2023	Adversarial RobustnessBinary Classification	—Unverified
Language-Driven Anchors for Zero-Shot Adversarial Robustness	Jan 30, 2023	Adversarial DefenseAdversarial Robustness	CodeCode Available
Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation	Jan 26, 2023	Adversarial RobustnessMuJoCo	—Unverified
Provable Unrestricted Adversarial Training without Compromise with Generalizability	Jan 22, 2023	Adversarial Robustness	—Unverified
Phase-shifted Adversarial Training	Jan 12, 2023	Adversarial Robustness	—Unverified
On adversarial robustness and the use of Wasserstein ascent-descent dynamics to enforce it	Jan 9, 2023	Adversarial Robustness	—Unverified
Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks	Jan 5, 2023	Adversarial Robustness	CodeCode Available
Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videos	Jan 3, 2023	Action RecognitionAdversarial Robustness	CodeCode Available
Towards Better Robustness against Common Corruptions for Unsupervised Domain Adaptation	Jan 1, 2023	Adversarial RobustnessData Augmentation	CodeCode Available
A New Dataset Based on Images Taken by Blind People for Testing the Robustness of Image Classification Models Trained for ImageNet Categories	Jan 1, 2023	Adversarial RobustnessClassification	CodeCode Available
Explaining Adversarial Robustness of Neural Networks from Clustering Effect Perspective	Jan 1, 2023	Adversarial AttackAdversarial Robustness	CodeCode Available

Show:10 25 50

← PrevPage 38 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