SOTAVerified

Adversarial Robustness

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 501–550 of 1746 papers

TitleStatusHype
Enhancing Adversarial Robustness via Uncertainty-Aware Distributional Adversarial Training—0
DiffPAD: Denoising Diffusion-based Adversarial Patch DecontaminationCode0
FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Training—0
CausAdv: A Causal-based Framework for Detecting Adversarial ExamplesCode0
Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions—0
Complexity Matters: Effective Dimensionality as a Measure for Adversarial Robustness—0
Conflict-Aware Adversarial Training—0
Beyond Pruning Criteria: The Dominant Role of Fine-Tuning and Adaptive Ratios in Neural Network Robustness—0
Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language ModelsCode0
A Hybrid Defense Strategy for Boosting Adversarial Robustness in Vision-Language Models—0
DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency DomainCode0
New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and Robustness via Dummy ClassesCode0
Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object DetectorsCode0
Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks—0
Understanding Adversarially Robust Generalization via Weight-Curvature Index—0
Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentation—0
Adversarial Robustness Overestimation and Instability in TRADES—0
Give me a hint: Can LLMs take a hint to solve math problems?Code0
Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models—0
Knowledge-Augmented Reasoning for EUAIA Compliance and Adversarial Robustness of LLMs—0
A Brain-Inspired Regularizer for Adversarial RobustnessCode0
Towards Assuring EU AI Act Compliance and Adversarial Robustness of LLMs—0
Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs—0
LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks—0
Fake It Until You Break It: On the Adversarial Robustness of AI-generated Image DetectorsCode0
MOREL: Enhancing Adversarial Robustness through Multi-Objective Representation Learning—0
Nonideality-aware training makes memristive networks more robust to adversarial attacksCode0
Improving Fast Adversarial Training via Self-Knowledge Guidance—0
Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training—0
Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation—0
Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training ApproachCode0
Training Safe Neural Networks with Global SDP Bounds—0
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains—0
FedProphet: Memory-Efficient Federated Adversarial Training via Theoretic-Robustness and Low-Inconsistency Cascade Learning—0
A Cost-Aware Approach to Adversarial Robustness in Neural Networks—0
Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Models—0
Adversarial Attacks on Data AttributionCode0
Limited but consistent gains in adversarial robustness by co-training object recognition models with human EEG—0
A practical approach to evaluating the adversarial distance for machine learning classifiersCode0
Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble—0
Reassessing Noise Augmentation Methods in the Context of Adversarial Speech—0
Lyapunov Neural ODE State-Feedback Control Policies—0
LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion ModelsCode0
Improving Adversarial Robustness in Android Malware Detection by Reducing the Impact of Spurious CorrelationsCode0
On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspective—0
Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach—0
Towards Efficient Formal Verification of Spiking Neural Network—0
Criticality Leveraged Adversarial Training (CLAT) for Boosted Performance via Parameter Efficiency—0
Segment-Anything Models Achieve Zero-shot Robustness in Autonomous DrivingCode0
Kolmogorov-Arnold Networks (KAN) for Time Series Classification and Robust AnalysisCode0
Show:102550
← PrevPage 11 of 35Next →
All datasetsAdvGLUECIFAR-10ImageNetImageNet-AImageNet-CStylized ImageNetCIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeBERTa (single model)Accuracy0.61—Unverified
2ALBERT (single model)Accuracy0.59—Unverified
3T5 (single model)Accuracy0.57—Unverified
4SMART_RoBERTa (single model)Accuracy0.54—Unverified
5FreeLB (single model)Accuracy0.5—Unverified
6RoBERTa (single model)Accuracy0.5—Unverified
7InfoBERT (single model)Accuracy0.46—Unverified
8ELECTRA (single model)Accuracy0.42—Unverified
9BERT (single model)Accuracy0.34—Unverified
10SMART_BERT (single model)Accuracy0.3—Unverified
#ModelMetricClaimedVerifiedStatus
1Mixed classifierAccuracy95.23—Unverified
2Stochastic-LWTA/PGD/WideResNet-34-10Accuracy92.26—Unverified
3Stochastic-LWTA/PGD/WideResNet-34-5Accuracy91.88—Unverified
4GLOT-DRAccuracy84.13—Unverified
5TRADES-ANCRA/ResNet18Accuracy81.7—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet-50 (SGD, Cosine)Accuracy77.4—Unverified
2ResNet-50 (SGD, Step)Accuracy76.9—Unverified
3DeiT-S (AdamW, Cosine)Accuracy76.8—Unverified
4ResNet-50 (AdamW, Cosine)Accuracy76.4—Unverified
#ModelMetricClaimedVerifiedStatus
1DeiT-S (AdamW, Cosine)Accuracy12.2—Unverified
2ResNet-50 (SGD, Cosine)Accuracy3.3—Unverified
3ResNet-50 (SGD, Step)Accuracy3.2—Unverified
4ResNet-50 (AdamW, Cosine)Accuracy3.1—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet-50 (AdamW, Cosine)mean Corruption Error (mCE)59.3—Unverified
2ResNet-50 (SGD, Step)mean Corruption Error (mCE)57.9—Unverified
3ResNet-50 (SGD, Cosine)mean Corruption Error (mCE)56.9—Unverified
4DeiT-S (AdamW, Cosine)mean Corruption Error (mCE)48—Unverified
#ModelMetricClaimedVerifiedStatus
1DeiT-S (AdamW, Cosine)Accuracy13—Unverified
2ResNet-50 (SGD, Cosine)Accuracy8.4—Unverified
3ResNet-50 (SGD, Step)Accuracy8.3—Unverified
4ResNet-50 (AdamW, Cosine)Accuracy8.1—Unverified
#ModelMetricClaimedVerifiedStatus
1Mixed ClassifierClean Accuracy85.21—Unverified
2ResNet18/MART-ANCRAClean Accuracy60.1—Unverified