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

Showing 301325 of 1808 papers

TitleStatusHype
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style TransferCode1
Boosting Adversarial Transferability via Gradient Relevance AttackCode1
Improving Query Efficiency of Black-box Adversarial AttackCode1
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
An Efficient Adversarial Attack for Tree EnsemblesCode1
OpenAttack: An Open-source Textual Adversarial Attack ToolkitCode1
Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack FrameworkCode1
NeuroUnlock: Unlocking the Architecture of Obfuscated Deep Neural NetworksCode1
Object Hider: Adversarial Patch Attack Against Object DetectorsCode1
Adversarial Attack and Defense of Structured Prediction ModelsCode1
On Evaluating Adversarial RobustnessCode1
CARBEN: Composite Adversarial Robustness BenchmarkCode1
An Extensive Study on Adversarial Attack against Pre-trained Models of CodeCode1
Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving ScenariosCode1
Certifying LLM Safety against Adversarial PromptingCode1
An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacksCode1
Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords SubstitutionCode1
SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM AgentsCode1
Combining GANs and AutoEncoders for Efficient Anomaly DetectionCode1
Fast Adversarial CNN-based Perturbation Attack of No-Reference Image Quality MetricsCode0
Extending Adversarial Attacks to Produce Adversarial Class Probability DistributionsCode0
Accelerated Stochastic Gradient-free and Projection-free MethodsCode0
Fashion-Guided Adversarial Attack on Person SegmentationCode0
Exploiting vulnerabilities of deep neural networks for privacy protectionCode0
Show:102550
← PrevPage 13 of 73Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Xu et al.Attack: PGD2078.68Unverified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13Unverified
3TRADES-ANCRA/ResNet18Attack: AutoAttack59.7Unverified
4AdvTraining [madry2018]Attack: PGD2048.44Unverified
5TRADES [zhang2019b]Attack: PGD2045.9Unverified
6XU-NetRobust Accuracy1Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85Unverified