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 151–200 of 1808 papers

TitleStatusHype
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency DomainCode1
Disentangled Information BottleneckCode1
Adversarial Attack and Defense in Deep RankingCode1
Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords SubstitutionCode1
Adversarial Ranking Attack and DefenseCode1
An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial TransferabilityCode1
Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving ScenariosCode1
EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability DetectionCode1
AdvDrop: Adversarial Attack to DNNs by Dropping InformationCode1
An Extensive Study on Adversarial Attack against Pre-trained Models of CodeCode1
A Review of Adversarial Attack and Defense for Classification MethodsCode1
Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language ModelsCode1
Adversarial Attack and Defense Strategies for Deep Speaker Recognition SystemsCode1
An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacksCode1
CausalAdv: Adversarial Robustness through the Lens of CausalityCode1
Adversarial Training with Fast Gradient Projection Method against Synonym Substitution based Text AttacksCode1
On the Multi-modal Vulnerability of Diffusion ModelsCode1
3D Gaussian Splat VulnerabilitiesCode1
Adversarial Examples in Deep Learning for Multivariate Time Series RegressionCode1
Are AlphaZero-like Agents Robust to Adversarial Perturbations?Code1
Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV TrackingCode1
A Pilot Study of Query-Free Adversarial Attack against Stable DiffusionCode1
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language ModelsCode1
Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution LearningCode1
Attacking Recommender Systems with Augmented User ProfilesCode1
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language ModelsCode1
Frequency-driven Imperceptible Adversarial Attack on Semantic SimilarityCode1
Adversarial Immunization for Certifiable Robustness on GraphsCode1
A Survey On Universal Adversarial AttackCode1
AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake DetectionCode1
Attack as the Best Defense: Nullifying Image-to-image Translation GANs via Limit-aware Adversarial AttackCode1
Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a BlinkCode1
Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query AttacksCode1
Adversarial Learning for Robust Deep ClusteringCode1
Adversarial Attack on Community Detection by Hiding IndividualsCode1
R&R: Metric-guided Adversarial Sentence GenerationCode1
A Unified Framework for Adversarial Attack and Defense in Constrained Feature SpaceCode1
GreedyFool: Distortion-Aware Sparse Adversarial AttackCode1
Adversarial Attack on Deep Learning-Based Splice LocalizationCode1
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box FrameworkCode1
High Frequency Component Helps Explain the Generalization of Convolutional Neural NetworksCode1
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock PredictionCode1
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock PredictionsCode1
CARBEN: Composite Adversarial Robustness BenchmarkCode1
Adversarial Vulnerability of Randomized EnsemblesCode1
Adversarial Magnification to Deceive Deepfake Detection through Super ResolutionCode1
AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion ModelsCode1
Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition ModelCode1
BayesOpt Adversarial AttackCode1
An Efficient Adversarial Attack for Tree EnsemblesCode1
Show:102550
← PrevPage 4 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