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 451–500 of 1808 papers

TitleStatusHype
RetouchUAA: Unconstrained Adversarial Attack via Image Retouching—0
Adversarial Purification of Information MaskingCode0
Trainwreck: A damaging adversarial attack on image classifiersCode0
When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence—0
AdvGen: Physical Adversarial Attack on Face Presentation Attack Detection Systems—0
Generating Valid and Natural Adversarial Examples with Large Language Models—0
Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts—0
DA^3: A Distribution-Aware Adversarial Attack against Language Models—0
An Extensive Study on Adversarial Attack against Pre-trained Models of CodeCode1
Learning Globally Optimized Language Structure via Adversarial Training—0
Robust Text Classification: Analyzing Prototype-Based NetworksCode0
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and FlatnessCode0
Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous—0
Resilient and constrained consensus against adversarial attacks: A distributed MPC framework—0
ABIGX: A Unified Framework for eXplainable Fault Detection and Classification—0
Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selectionCode0
Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems—0
LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbations—0
Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement LearningCode0
Differentially Private Reward Estimation with Preference Feedback—0
Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors—0
Adversarial sample generation and training using geometric masks for accurate and resilient license plate character recognitionCode0
Semantic-Aware Adversarial Training for Reliable Deep Hashing RetrievalCode0
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language ModelsCode1
Imperceptible CMOS camera dazzle for adversarial attacks on deep neural networks—0
CT-GAT: Cross-Task Generative Adversarial Attack based on TransferabilityCode0
Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-AugmentingCode0
SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation—0
Adversarial Training for Physics-Informed Neural NetworksCode0
Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks—0
Evading Detection Actively: Toward Anti-Forensics against Forgery Localization—0
Black-box Targeted Adversarial Attack on Segment Anything (SAM)—0
A Non-monotonic Smooth Activation Function—0
Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion ModelsCode0
Adversarial optimization leads to over-optimistic security-constrained dispatch, but sampling can help—0
Targeted Attack Improves Protection against Unauthorized Diffusion CustomizationCode1
Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection System—0
Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion CriteriaCode0
Optimizing Key-Selection for Face-based One-Time Biometrics via Morphing—0
Adversarial Client Detection via Non-parametric Subspace Monitoring in the Internet of Federated Things—0
Robustness of AI-Image Detectors: Fundamental Limits and Practical AttacksCode1
Gray-box Adversarial Attack of Deep Reinforcement Learning-based Trading Agents—0
Structure Invariant Transformation for better Adversarial TransferabilityCode1
Understanding Pose and Appearance Disentanglement in 3D Human Pose Estimation—0
PRAT: PRofiling Adversarial aTtacks—0
Model Leeching: An Extraction Attack Targeting LLMs—0
Transferable Adversarial Attack on Image Tampering Localization—0
Context-aware Adversarial Attack on Named Entity Recognition—0
Semantic Adversarial Attacks via Diffusion ModelsCode1
PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection—0
Show:102550
← PrevPage 10 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