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 201–250 of 1808 papers

TitleStatusHype
Multi-attacks: Many images + the same adversarial attack many target labelsCode1
To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning ModelsCode1
Adversarial Attack on Large Scale GraphCode1
Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack FrameworkCode1
Natural Color Fool: Towards Boosting Black-box Unrestricted AttacksCode1
Nesterov Accelerated Gradient and Scale Invariance for Adversarial AttacksCode1
AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric LearningCode1
Certifying LLM Safety against Adversarial PromptingCode1
Adversarial Ranking Attack and DefenseCode1
On Evaluating Adversarial RobustnessCode1
Adversarial Attack On Yolov5 For Traffic And Road Sign DetectionCode1
CARBEN: Composite Adversarial Robustness BenchmarkCode1
Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNsCode1
CgAT: Center-Guided Adversarial Training for Deep Hashing-Based RetrievalCode1
High Frequency Component Helps Explain the Generalization of Convolutional Neural NetworksCode1
Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords SubstitutionCode1
On the Robustness of Safe Reinforcement Learning under Observational PerturbationsCode1
On the Multi-modal Vulnerability of Diffusion ModelsCode1
CausalAdv: Adversarial Robustness through the Lens of CausalityCode1
OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated ExamplesCode1
Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-ArtCode1
CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating DeepfakesCode1
Contextualized Perturbation for Textual Adversarial AttackCode1
Adversarial Self-Supervised Contrastive LearningCode1
An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial TransferabilityCode1
Phrase-level Textual Adversarial Attack with Label PreservationCode1
AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion ModelsCode1
Adversarial Training for Free!Code1
Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible NoisesCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Adversarial Vulnerabilities in Large Language Models for Time Series ForecastingCode1
Adversarial Vulnerability of Randomized EnsemblesCode1
DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-DomainCode1
Preserving Semantics in Textual Adversarial AttacksCode1
Differentiable JPEG: The Devil is in the DetailsCode1
Proximal Splitting Adversarial Attack for Semantic SegmentationCode1
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot NavigationCode1
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing FlowsCode1
RayS: A Ray Searching Method for Hard-label Adversarial AttackCode1
Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural NetworksCode1
Rethinking Image Restoration for Object DetectionCode1
Revealing Vulnerabilities in Stable Diffusion via Targeted AttacksCode1
Adv-Makeup: A New Imperceptible and Transferable Attack on Face RecognitionCode1
Deep Feature Space Trojan Attack of Neural Networks by Controlled DetoxificationCode1
Robust Deep Reinforcement Learning through Adversarial LossCode1
Robust Mid-Pass Filtering Graph Convolutional NetworksCode1
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted AttackCode1
Defending and Harnessing the Bit-Flip Based Adversarial Weight AttackCode1
Alleviating Adversarial Attacks on Variational Autoencoders with MCMCCode1
Disentangled Information BottleneckCode1
Show:102550
← PrevPage 5 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