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 301–350 of 1808 papers

TitleStatusHype
Imperceptible Face Forgery Attack via Adversarial Semantic MaskCode0
Explainable Graph Neural Networks Under FireCode0
DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attacks—0
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner—0
VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise—0
Graph Neural Network Explanations are FragileCode0
DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-DomainCode1
SVASTIN: Sparse Video Adversarial Attack via Spatio-Temporal Invertible Neural NetworksCode0
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular DataCode1
Disrupting Diffusion: Token-Level Attention Erasure Attack against Diffusion-based CustomizationCode1
Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function PriorCode0
Wavelet-Based Image Tokenizer for Vision Transformers—0
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack—0
Uncertainty Measurement of Deep Learning System based on the Convex Hull of Training Sets—0
Adversarial Attacks on Hidden Tasks in Multi-Task Learning—0
Rethinking Independent Cross-Entropy Loss For Graph-Structured DataCode0
AdjointDEIS: Efficient Gradients for Diffusion ModelsCode0
LookHere: Vision Transformers with Directed Attention Generalize and ExtrapolateCode0
Trustworthy Actionable Perturbations—0
Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors—0
Adversarial Robustness for Visual Grounding of Multimodal Large Language ModelsCode0
DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy ProtectionCode2
Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer—0
Disttack: Graph Adversarial Attacks Toward Distributed GNN TrainingCode0
Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing—0
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 7 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