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 1551–1575 of 1808 papers

TitleStatusHype
CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator—0
Semantic Image Attack for Visual Model Diagnosis—0
Semantic Preserving Adversarial Attack Generation with Autoencoder and Genetic Algorithm—0
Model Robustness with Text Classification: Semantic-preserving adversarial attacks—0
Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks?—0
Can We Really Trust Explanations? Evaluating the Stability of Feature Attribution Explanation Methods via Adversarial Attack—0
Can We Rely on AI?—0
SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models—0
CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purification—0
Capsule Neural Networks as Noise Stabilizer for Time Series Data—0
Attacking Perceptual Similarity Metrics—0
Attacking Important Pixels for Anchor-free Detectors—0
Certifiably Robust Variational Autoencoders—0
SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images—0
Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation—0
Chain Association-based Attacking and Shielding Natural Language Processing Systems—0
Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems—0
Channel-Aware Adversarial Attacks Against Deep Learning-Based Wireless Signal Classifiers—0
Channel Effects on Surrogate Models of Adversarial Attacks against Wireless Signal Classifiers—0
Attack-Agnostic Adversarial Detection—0
CharBot: A Simple and Effective Method for Evading DGA Classifiers—0
Sequential Attacks on Agents for Long-Term Adversarial Goals—0
A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays—0
Class-Aware Domain Adaptation for Improving Adversarial Robustness—0
Class-based Prediction Errors to Detect Hate Speech with Out-of-vocabulary Words—0
Show:102550
← PrevPage 63 of 73Next →
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