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 1301–1350 of 1808 papers

TitleStatusHype
Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent Representations—0
Improving Robustness of Task Oriented Dialog Systems—0
ODE guided Neural Data Augmentation Techniques for Time Series Data and its Benefits on Robustness—0
Improving the JPEG-resistance of Adversarial Attacks on Face Recognition by Interpolation Smoothing—0
Improving the Transferability of Adversarial Examples by Inverse Knowledge Distillation—0
Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentation—0
Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing—0
Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restoration—0
Improving Visual Quality of Unrestricted Adversarial Examples with Wavelet-VAE—0
Influence Based Defense Against Data Poisoning Attacks in Online Learning—0
"Influence Sketching": Finding Influential Samples In Large-Scale Regressions—0
Information Importance-Aware Defense against Adversarial Attack for Automatic Modulation Classification:An XAI-Based Approach—0
Inline Detection of DGA Domains Using Side Information—0
Input Hessian Regularization of Neural Networks—0
Input-Specific and Universal Adversarial Attack Generation for Spiking Neural Networks in the Spiking Domain—0
Input-specific Attention Subnetworks for Adversarial Detection—0
Input-specific Attention Subnetworks for Adversarial Detection—0
Intermediate Level Adversarial Attack for Enhanced Transferability—0
Intermediate Outputs Are More Sensitive Than You Think—0
Internal Wasserstein Distance for Adversarial Attack and Defense—0
Interpolation between CNNs and ResNets—0
Interpreting and Evaluating Neural Network Robustness—0
Interpreting Hidden Semantics in the Intermediate Layers of 3D Point Cloud Classification Neural Network—0
Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search—0
MF-CLIP: Leveraging CLIP as Surrogate Models for No-box Adversarial Attacks—0
Adversarial Attacks on Time-Series Intrusion Detection for Industrial Control Systems—0
Exploring the Robustness of NMT Systems to Nonsensical Inputs—0
Investigating Decision Boundaries of Trained Neural Networks—0
Investigating Resistance of Deep Learning-based IDS against Adversaries using min-max Optimization—0
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems—0
Investigating Vulnerability to Adversarial Examples on Multimodal Data Fusion in Deep Learning—0
I See Dead People: Gray-Box Adversarial Attack on Image-To-Text Models—0
Learning Task-aware Robust Deep Learning Systems—0
Is It Time to Redefine the Classification Task for Deep Learning Systems?—0
Isolated and Ensemble Audio Preprocessing Methods for Detecting Adversarial Examples against Automatic Speech Recognition—0
Iterative Adversarial Attack on Image-guided Story Ending Generation—0
ITPatch: An Invisible and Triggered Physical Adversarial Patch against Traffic Sign Recognition—0
Adversarial Rain Attack and Defensive Deraining for DNN Perception—0
JailbreakHunter: A Visual Analytics Approach for Jailbreak Prompts Discovery from Large-Scale Human-LLM Conversational Datasets—0
Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts—0
Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models—0
Jitter Does Matter: Adapting Gaze Estimation to New Domains—0
Just One Moment: Structural Vulnerability of Deep Action Recognition against One Frame Attack—0
Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System—0
KoDF: A Large-scale Korean DeepFake Detection Dataset—0
Label Smoothing and Adversarial Robustness—0
LanCe: A Comprehensive and Lightweight CNN Defense Methodology against Physical Adversarial Attacks on Embedded Multimedia Applications—0
Large-Scale Adversarial Attacks on Graph Neural Networks via Graph Coarsening—0
Latent Magic: An Investigation into Adversarial Examples Crafted in the Semantic Latent Space—0
LEA2: A Lightweight Ensemble Adversarial Attack via Non-overlapping Vulnerable Frequency Regions—0
Show:102550
← PrevPage 27 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