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 26–50 of 1808 papers

TitleStatusHype
Adversarial Semantic and Label Perturbation Attack for Pedestrian Attribute RecognitionCode0
Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack—0
TabAttackBench: A Benchmark for Adversarial Attacks on Tabular DataCode0
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal AlignmentCode2
A Framework for Adversarial Analysis of Decision Support Systems Prior to Deployment—0
Boosting Adversarial Transferability via High-Frequency Augmentation and Hierarchical-Gradient Fusion—0
TESSER: Transfer-Enhancing Adversarial Attacks from Vision Transformers via Spectral and Semantic Regularization—0
Curvature Dynamic Black-box Attack: revisiting adversarial robustness via dynamic curvature estimation—0
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box FrameworkCode1
Ownership Verification of DNN Models Using White-Box Adversarial Attacks with Specified Probability Manipulation—0
Temporal Consistency Constrained Transferable Adversarial Attacks with Background Mixup for Action RecognitionCode0
Towards more transferable adversarial attack in black-box manner—0
Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms—0
Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems—0
Experimental robustness benchmark of quantum neural network on a superconducting quantum processor—0
Beyond Classification: Evaluating Diffusion Denoised Smoothing for Security-Utility Trade off—0
Adverseness vs. Equilibrium: Exploring Graph Adversarial Resilience through Dynamic Equilibrium—0
EVALOOP: Assessing LLM Robustness in Programming from a Self-consistency Perspective—0
FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Models—0
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation ModelsCode1
Adversarial Attack on Large Language Models using Exponentiated Gradient DescentCode0
Evaluating the Robustness of Adversarial Defenses in Malware Detection SystemsCode0
Towards Adaptive Meta-Gradient Adversarial Examples for Visual TrackingCode0
No Query, No Access—0
Input-Specific and Universal Adversarial Attack Generation for Spiking Neural Networks in the Spiking Domain—0
Show:102550
← PrevPage 2 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