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 651–700 of 1808 papers

TitleStatusHype
Boosting Adversarial Transferability using Dynamic Cues—0
An Incremental Gray-box Physical Adversarial Attack on Neural Network Training—0
Variation Enhanced Attacks Against RRAM-based Neuromorphic Computing System—0
Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective—0
X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item DetectionCode1
Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements—0
StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot LearningCode1
Graph Adversarial Immunization for Certifiable RobustnessCode0
Robust Mid-Pass Filtering Graph Convolutional NetworksCode1
Threatening Patch Attacks on Object Detection in Optical Remote Sensing ImagesCode0
TextDefense: Adversarial Text Detection based on Word Importance Entropy—0
Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend—0
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classification—0
TransFool: An Adversarial Attack against Neural Machine Translation ModelsCode0
Universal Soldier: Using Universal Adversarial Perturbations for Detecting Backdoor Attacks—0
The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models—0
Improving Adversarial Transferability with Scheduled Step Size and Dual Example—0
Identifying Adversarially Attackable and Robust SamplesCode0
Analyzing Robustness of the Deep Reinforcement Learning Algorithm in Ramp Metering Applications Considering False Data Injection Attack and Defense—0
Semantic Adversarial Attacks on Face Recognition through Significant Attributes—0
Targeted Attacks on Timeseries Forecasting—0
Attacking Important Pixels for Anchor-free Detectors—0
On the Adversarial Robustness of Camera-based 3D Object DetectionCode1
DODEM: DOuble DEfense Mechanism Against Adversarial Attacks Towards Secure Industrial Internet of Things Analytics—0
On the feasibility of attacking Thai LPR systems with adversarial examples—0
On the Susceptibility and Robustness of Time Series Models through Adversarial Attack and Defense—0
Availability Adversarial Attack and Countermeasures for Deep Learning-based Load ForecastingCode0
Boosting Adversarial Transferability via Gradient Relevance AttackCode1
F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives—0
Transferable Adversarial Attack for Both Vision Transformers and Convolutional Networks via Momentum Integrated Gradients—0
LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions—0
Explaining Adversarial Robustness of Neural Networks from Clustering Effect PerspectiveCode0
Frequency-aware GAN for Adversarial Manipulation Generation—0
Black-Box Sparse Adversarial Attack via Multi-Objective Optimisation—0
Proximal Splitting Adversarial Attack for Semantic SegmentationCode1
The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection—0
BiasAdv: Bias-Adversarial Augmentation for Model Debiasing—0
Towards Transferable Targeted Adversarial ExamplesCode0
RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural PromptsCode1
Angelic Patches for Improving Third-Party Object Detector PerformanceCode0
ExploreADV: Towards exploratory attack for Neural Networks—0
Generalizable Black-Box Adversarial Attack with Meta LearningCode1
Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence—0
Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch AttacksCode1
Multi-head Uncertainty Inference for Adversarial Attack Detection—0
Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face RecognitionCode1
AI Security for Geoscience and Remote Sensing: Challenges and Future Trends—0
Alternating Objectives Generates Stronger PGD-Based Adversarial Attacks—0
Adversarial Attacks and Defences for Skin Cancer Classification—0
Show:102550
← PrevPage 14 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