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 601–650 of 1808 papers

TitleStatusHype
AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack—0
A Non-monotonic Smooth Activation Function—0
Evaluations and Methods for Explanation through Robustness Analysis—0
Experimental robustness benchmark of quantum neural network on a superconducting quantum processor—0
Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples—0
Exploiting Vulnerability of Pooling in Convolutional Neural Networks by Strict Layer-Output Manipulation for Adversarial Attacks—0
Fair Robust Active Learning by Joint Inconsistency—0
Adversarial defenses via a mixture of generators—0
DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking—0
Attacking c-MARL More Effectively: A Data Driven Approach—0
Adversarial Defense based on Structure-to-Signal Autoencoders—0
Differentially Private Reward Estimation with Preference Feedback—0
Evaluating Neural Model Robustness for Machine Comprehension—0
Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack—0
Adversarial Data Encryption—0
A critique of the DeepSec Platform for Security Analysis of Deep Learning Models—0
An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms—0
Device-aware Optical Adversarial Attack for a Portable Projector-camera System—0
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning—0
Adversarial Color Projection: A Projector-based Physical Attack to DNNs—0
Evaluating Deep Learning Models and Adversarial Attacks on Accelerometer-Based Gesture Authentication—0
Evaluating the Robustness of LiDAR Point Cloud Tracking Against Adversarial Attack—0
Adversarial Body Shape Search for Legged Robots—0
An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter—0
DFT-Based Adversarial Attack Detection in MRI Brain Imaging: Enhancing Diagnostic Accuracy in Alzheimer's Case Studies—0
ErasableMask: A Robust and Erasable Privacy Protection Scheme against Black-box Face Recognition Models—0
A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger's Adversarial Attacks—0
An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks—0
Detecting and Segmenting Adversarial Graphics Patterns from Images—0
Adversarial Client Detection via Non-parametric Subspace Monitoring in the Internet of Federated Things—0
Evading Detection Actively: Toward Anti-Forensics against Forgery Localization—0
Differential Privacy in Personalized Pricing with Nonparametric Demand Models—0
An Incremental Gray-box Physical Adversarial Attack on Neural Network Training—0
Diffusion Attack: Leveraging Stable Diffusion for Naturalistic Image Attacking—0
3DGAA: Realistic and Robust 3D Gaussian-based Adversarial Attack for Autonomous Driving—0
An Empirical Analysis of Federated Learning Models Subject to Label-Flipping Adversarial Attack—0
Anomaly Detection in Unsupervised Surveillance Setting Using Ensemble of Multimodal Data with Adversarial Defense—0
Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions—0
An Efficient and Margin-Approaching Zero-Confidence Adversarial Attack—0
EVALOOP: Assessing LLM Robustness in Programming from a Self-consistency Perspective—0
Design of secure and robust cognitive system for malware detection—0
Adversarial-Aware Deep Learning System based on a Secondary Classical Machine Learning Verification Approach—0
Derivation of Information-Theoretically Optimal Adversarial Attacks with Applications to Robust Machine Learning—0
OGAN: Disrupting Deepfakes with an Adversarial Attack that Survives Training—0
Democratic Training Against Universal Adversarial Perturbations—0
Activation Learning by Local Competitions—0
Distillation-Enhanced Physical Adversarial Attacks—0
A Novel Deep Learning based Model to Defend Network Intrusion Detection System against Adversarial Attacks—0
Enhancing Transferability of Adversarial Attacks with GE-AdvGAN+: A Comprehensive Framework for Gradient Editing—0
Analyzing the Noise Robustness of Deep Neural Networks—0
Show:102550
← PrevPage 13 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