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 326–350 of 1808 papers

TitleStatusHype
Muting Whisper: A Universal Acoustic Adversarial Attack on Speech Foundation ModelsCode1
BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimization—0
Universal Adversarial Perturbations for Vision-Language Pre-trained ModelsCode1
Untargeted Adversarial Attack on Knowledge Graph Embeddings—0
Revisiting Character-level Adversarial Attacks for Language ModelsCode1
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models—0
Probing Unlearned Diffusion Models: A Transferable Adversarial Attack PerspectiveCode0
An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat LandscapeCode1
A General Black-box Adversarial Attack on Graph-based Fake News Detectors—0
DIP-Watermark: A Double Identity Protection Method Based on Robust Adversarial Watermark—0
Beyond Score Changes: Adversarial Attack on No-Reference Image Quality Assessment from Two Perspectives—0
AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation—0
SA-Attack: Speed-adaptive stealthy adversarial attack on trajectory predictionCode0
Adversarial Identity Injection for Semantic Face Image Synthesis—0
Towards a Novel Perspective on Adversarial Examples Driven by Frequency—0
Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of ArtifactsCode0
Towards Building a Robust Toxicity Predictor—0
BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack—0
Adversarial Attacks and Dimensionality in Text Classifiers—0
Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models—0
READ: Improving Relation Extraction from an ADversarial PerspectiveCode0
Multi-granular Adversarial Attacks against Black-box Neural Ranking Models—0
Patch Synthesis for Property Repair of Deep Neural Networks—0
Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial AttackCode2
The Double-Edged Sword of Input Perturbations to Robust Accurate Fairness—0
Show:102550
← PrevPage 14 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