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 401–450 of 1746 papers

TitleStatusHype
A Curious Case of Remarkable Resilience to Gradient Attacks via Fully Convolutional and Differentiable Front End with a Skip Connection—0
An Adversarial Robustness Benchmark for Enterprise Network Intrusion Detection—0
Spectrum Extraction and Clipping for Implicitly Linear LayersCode0
Distilling Adversarial Robustness Using Heterogeneous Teachers—0
On the Duality Between Sharpness-Aware Minimization and Adversarial TrainingCode1
A Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothing—0
Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial ImageCode1
Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM AssessmentCode1
Evolutionary Reinforcement Learning: A Systematic Review and Future Directions—0
Evaluating Adversarial Robustness of Low dose CT RecoveryCode0
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual ModelsCode0
Maintaining Adversarial Robustness in Continuous Learning—0
DART: A Principled Approach to Adversarially Robust Unsupervised Domain Adaptation—0
VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models—0
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding SpaceCode1
Reducing Texture Bias of Deep Neural Networks via Edge Enhancing DiffusionCode0
Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring—0
Two Tales of Single-Phase Contrastive Hebbian LearningCode0
Tighter Bounds on the Information Bottleneck with Application to Deep LearningCode0
A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense—0
RAMP: Boosting Adversarial Robustness Against Multiple l_p Perturbations for Universal RobustnessCode0
TETRIS: Towards Exploring the Robustness of Interactive Segmentation—0
Is Adversarial Training with Compressed Datasets Effective?Code0
A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs—0
Adversarial Robustness Through Artifact Design—0
Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons—0
Partially Recentralization Softmax Loss for Vision-Language Models Robustness—0
Exploring Biologically Inspired Mechanisms of Adversarial Robustness—0
Causal Feature Selection for Responsible Machine Learning—0
Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-errorCode1
MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed ClassifiersCode0
σ-zero: Gradient-based Optimization of _0-norm Adversarial ExamplesCode1
Delving into Decision-based Black-box Attacks on Semantic Segmentation—0
Achieving More Human Brain-Like Vision via Human EEG Representational Alignment—0
GPS: Graph Contrastive Learning via Multi-scale Augmented Views from Adversarial Pooling—0
Mitigating the Impact of Noisy Edges on Graph-Based Algorithms via Adversarial Robustness Evaluation—0
AFD: Mitigating Feature Gap for Adversarial Robustness by Feature DisentanglementCode0
Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective—0
A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE)Code0
Fast Adversarial Training against Textual Adversarial Attacks—0
CARE: Ensemble Adversarial Robustness Evaluation Against Adaptive Attackers for Security Applications—0
The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness—0
Adversarial Robustness of Link Sign Prediction in Signed Graphs—0
Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers—0
Universally Robust Graph Neural Networks by Preserving Neighbor Similarity—0
The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical ImagesCode1
Authorship Obfuscation in Multilingual Machine-Generated Text DetectionCode2
Robustness Against Adversarial Attacks via Learning Confined Adversarial Polytopes—0
Adversarial Examples are Misaligned in Diffusion Model Manifolds—0
Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial RobustnessCode1
Show:102550
← PrevPage 9 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