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 901–950 of 1808 papers

TitleStatusHype
Practical Order Attack in Deep Ranking—0
PRAT: PRofiling Adversarial aTtacks—0
Prepared for the Worst: A Learning-Based Adversarial Attack for Resilience Analysis of the ICP Algorithm—0
Preventing Non-intrusive Load Monitoring Privacy Invasion: A Precise Adversarial Attack Scheme for Networked Smart Meters—0
Prior Networks for Detection of Adversarial Attacks—0
Privacy Protection in Personalized Diffusion Models via Targeted Cross-Attention Adversarial Attack—0
Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage—0
Probabilistic Categorical Adversarial Attack & Adversarial Training—0
Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection—0
Probing Model Signal-Awareness via Prediction-Preserving Input Minimization—0
Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach—0
ProjAttacker: A Configurable Physical Adversarial Attack for Face Recognition via Projector—0
Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attack on Breast Ultrasound Images—0
Prompt-driven Transferable Adversarial Attack on Person Re-Identification with Attribute-aware Textual Inversion—0
Propagated Perturbation of Adversarial Attack for well-known CNNs: Empirical Study and its Explanation—0
PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks—0
Protection against Cloning for Deep Learning—0
Protego: Detecting Adversarial Examples for Vision Transformers via Intrinsic Capabilities—0
Protein Folding Neural Networks Are Not Robust—0
Pseudo-Conversation Injection for LLM Goal Hijacking—0
Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation—0
QFAL: Quantum Federated Adversarial Learning—0
Query-Efficient Black-Box Attack by Active Learning—0
Query-Efficient Hard-Label Black-Box Attack against Vision Transformers—0
Query-Efficient Video Adversarial Attack with Stylized Logo—0
Query-Free Adversarial Transfer via Undertrained Surrogates—0
Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs—0
RAF: Recursive Adversarial Attacks on Face Recognition Using Extremely Limited Queries—0
Attack Agnostic Detection of Adversarial Examples via Random Subspace Analysis—0
RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors—0
The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples—0
Realistic Scatterer Based Adversarial Attacks on SAR Image Classifiers—0
Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks—0
Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems—0
Real-World Adversarial Examples involving Makeup Application—0
Reasoning Chain Based Adversarial Attack for Multi-hop Question Answering—0
Text Adversarial Purification as Defense against Adversarial Attacks—0
Recent Advances in Reliable Deep Graph Learning: Inherent Noise, Distribution Shift, and Adversarial Attack—0
Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements—0
RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense—0
Redefining Machine Unlearning: A Conformal Prediction-Motivated Approach—0
Refining Adaptive Zeroth-Order Optimization at Ease—0
Region-Wise Attack: On Efficient Generation of Robust Physical Adversarial Examples—0
Reinforce Attack: Adversarial Attack against BERT with Reinforcement Learning—0
Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models—0
ReLATE: Resilient Learner Selection for Multivariate Time-Series Classification Against Adversarial Attacks—0
Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models—0
Residue-Based Natural Language Adversarial Attack Detection—0
Resilient and constrained consensus against adversarial attacks: A distributed MPC framework—0
Resilient Dynamic Average Consensus based on Trusted agents—0
Show:102550
← PrevPage 19 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