SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1501–1550 of 1808 papers

TitleStatusHype
A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays—0
Adversarial Imitation Attack—0
Challenging the adversarial robustness of DNNs based on error-correcting output codes—0
Solving Non-Convex Non-Differentiable Min-Max Games using Proximal Gradient Method—0
Inline Detection of DGA Domains Using Side Information—0
Frequency-Tuned Universal Adversarial Attacks—0
Using an ensemble color space model to tackle adversarial examples—0
SAD: Saliency-based Defenses Against Adversarial Examples—0
Gradient-based adversarial attacks on categorical sequence models via traversing an embedded world—0
No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial Attacks—0
Search Space of Adversarial Perturbations against Image Filters—0
Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems—0
Double Backpropagation for Training Autoencoders against Adversarial Attack—0
Security of Deep Learning based Lane Keeping System under Physical-World Adversarial Attack—0
Applying Tensor Decomposition to image for Robustness against Adversarial Attack—0
Adversarial Attack on Deep Product Quantization Network for Image Retrieval—0
Temporal Sparse Adversarial Attack on Sequence-based Gait Recognition—0
A Bayes-Optimal View on Adversarial Examples—0
Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient DescentCode0
Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack—0
Undersensitivity in Neural Reading Comprehension—0
Adversarial Data Encryption—0
Over-the-Air Adversarial Attacks on Deep Learning Based Modulation Classifier over Wireless Channels—0
DANCE: Enhancing saliency maps using decoysCode0
Practical Fast Gradient Sign Attack against Mammographic Image Classifier—0
Analyzing the Noise Robustness of Deep Neural Networks—0
Massif: Interactive Interpretation of Adversarial Attacks on Deep Learning—0
Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNet—0
Generating Semantic Adversarial Examples via Feature Manipulation—0
Interpolation between CNNs and ResNets—0
Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient—0
Implicit Euler Skip Connections: Enhancing Adversarial Robustness via Numerical Stability—0
Benchmarking Adversarial Robustness—0
Geometry-Aware Generation of Adversarial Point CloudsCode0
DAmageNet: A Universal Adversarial DatasetCode0
On-manifold Adversarial Data Augmentation Improves Uncertainty Calibration—0
CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator—0
Potential adversarial samples for white-box attacks—0
Amora: Black-box Adversarial Morphing Attack—0
Region-Wise Attack: On Efficient Generation of Robust Physical Adversarial Examples—0
Scratch that! An Evolution-based Adversarial Attack against Neural NetworksCode0
AdvPC: Transferable Adversarial Perturbations on 3D Point CloudsCode0
Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of ComponentsCode0
Light-weight Calibrator: a Separable Component for Unsupervised Domain AdaptationCode0
Towards Security Threats of Deep Learning Systems: A Survey—0
ColorFool: Semantic Adversarial ColorizationCode0
Adversarial Attack with Pattern Replacement—0
Time-aware Gradient Attack on Dynamic Network Link Prediction—0
Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion ReductionCode0
Heuristic Black-box Adversarial Attacks on Video Recognition ModelsCode0
Show:102550
← PrevPage 31 of 37Next →
All datasetsCIFAR-10CIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Xu et al.Attack: PGD2078.68—Unverified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13—Unverified
3TRADES-ANCRA/ResNet18Attack: AutoAttack59.7—Unverified
4AdvTraining [madry2018]Attack: PGD2048.44—Unverified
5TRADES [zhang2019b]Attack: PGD2045.9—Unverified
6XU-NetRobust Accuracy1—Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28—Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85—Unverified