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 1351–1400 of 1808 papers

TitleStatusHype
Learn2Weight: Weights Transfer Defense against Similar-domain Adversarial Attacks—0
Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations—0
Learning deep forest with multi-scale Local Binary Pattern features for face anti-spoofing—0
Learning Globally Optimized Language Structure via Adversarial Training—0
Learning Key Steps to Attack Deep Reinforcement Learning Agents—0
Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations—0
Learning to Defend by Learning to Attack—0
Learning to Defense by Learning to Attack—0
Learning to Detect Adversarial Examples Based on Class Scores—0
Left-right Discrepancy for Adversarial Attack on Stereo Networks—0
Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies—0
Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend—0
LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbations—0
Light Lies: Optical Adversarial Attack—0
Limited Budget Adversarial Attack Against Online Image Stream—0
Linear Backpropagation Leads to Faster Convergence—0
Linear system security -- detection and correction of adversarial attacks in the noise-free case—0
LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper—0
Local Competition and Stochasticity for Adversarial Robustness in Deep Learning—0
Local Competition and Uncertainty for Adversarial Robustness in Deep Learning—0
Localized Adversarial Training for Increased Accuracy and Robustness in Image Classification—0
LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model—0
Looking From the Future: Multi-order Iterations Can Enhance Adversarial Attack Transferability—0
L_p-norm Distortion-Efficient Adversarial Attack—0
L-RED: Efficient Post-Training Detection of Imperceptible Backdoor Attacks without Access to the Training Set—0
LSDAT: Low-Rank and Sparse Decomposition for Decision-based Adversarial Attack—0
MAA: Meticulous Adversarial Attack against Vision-Language Pre-trained Models—0
Make the Most of Everything: Further Considerations on Disrupting Diffusion-based Customization—0
MARAGE: Transferable Multi-Model Adversarial Attack for Retrieval-Augmented Generation Data Extraction—0
Massif: Interactive Interpretation of Adversarial Attacks on Deep Learning—0
MathAttack: Attacking Large Language Models Towards Math Solving Ability—0
Fast Inference of Removal-Based Node InfluenceCode0
Fast Adversarial CNN-based Perturbation Attack of No-Reference Image Quality MetricsCode0
Fashion-Guided Adversarial Attack on Person SegmentationCode0
FDA: Feature Disruptive AttackCode0
A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding ModelsCode0
Versatile Weight Attack via Flipping Limited BitsCode0
Extending Adversarial Attacks to Produce Adversarial Class Probability DistributionsCode0
Feature Space Perturbations Yield More Transferable Adversarial ExamplesCode0
The Limitations of Deep Learning in Adversarial SettingsCode0
The LogBarrier adversarial attack: making effective use of decision boundary informationCode0
Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial AttackCode0
Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate GradientsCode0
FenceBox: A Platform for Defeating Adversarial Examples with Data Augmentation TechniquesCode0
Adversarial Images for Variational AutoencodersCode0
The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement LearningCode0
Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial AttackCode0
Patch augmentation: Towards efficient decision boundaries for neural networksCode0
FireBERT: Hardening BERT-based classifiers against adversarial attackCode0
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and FlatnessCode0
Show:102550
← PrevPage 28 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