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 251–300 of 1808 papers

TitleStatusHype
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean LabelCode1
Towards Resistant Audio Adversarial ExamplesCode1
Towards Transferable Targeted 3D Adversarial Attack in the Physical WorldCode1
Towards Transferable Unrestricted Adversarial Examples with Minimum ChangesCode1
AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake DetectionCode1
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
Augmented Lagrangian Adversarial AttacksCode1
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box FrameworkCode1
A Unified Framework for Adversarial Attack and Defense in Constrained Feature SpaceCode1
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock PredictionsCode1
An Extensive Study on Adversarial Attack against Pre-trained Models of CodeCode1
AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric LearningCode1
AdvDrop: Adversarial Attack to DNNs by Dropping InformationCode1
Benchmarking Adversarial Robustness on Image ClassificationCode1
BERT-ATTACK: Adversarial Attack Against BERT Using BERTCode1
Boosting Adversarial Transferability via Gradient Relevance AttackCode1
Boosting the Adversarial Transferability of Surrogate Models with Dark KnowledgeCode1
Boosting the Transferability of Video Adversarial Examples via Temporal TranslationCode1
To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning ModelsCode1
An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat LandscapeCode1
Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords SubstitutionCode1
AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion ModelsCode1
CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating DeepfakesCode1
An Efficient Adversarial Attack for Tree EnsemblesCode1
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular DataCode1
Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation ModelsCode1
Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible NoisesCode1
A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical FlowCode1
Defending and Harnessing the Bit-Flip Based Adversarial Weight AttackCode1
Defending Your Voice: Adversarial Attack on Voice ConversionCode1
Defensive Distillation based Adversarial Attacks Mitigation Method for Channel Estimation using Deep Learning Models in Next-Generation Wireless NetworksCode1
Adversarial Attacks on ML Defense Models CompetitionCode1
Differentiable JPEG: The Devil is in the DetailsCode1
Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency DomainCode1
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language ModelsCode1
BASAR:Black-box Attack on Skeletal Action RecognitionCode1
Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic SegmentationCode1
DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural NetworksCode1
An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial TransferabilityCode1
An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacksCode1
Certifying LLM Safety against Adversarial PromptingCode1
Ensemble everything everywhere: Multi-scale aggregation for adversarial robustnessCode1
epsilon-Mesh Attack: A Surface-based Adversarial Point Cloud Attack for Facial Expression RecognitionCode1
Fooling the Image Dehazing Models by First Order GradientCode1
Fast and Low-Cost Genomic Foundation Models via Outlier RemovalCode1
Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based CustomizationCode1
FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial AttackCode1
Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point CloudsCode1
On the Adversarial Robustness of Camera-based 3D Object DetectionCode1
Show:102550
← PrevPage 6 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