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 76–100 of 1808 papers

TitleStatusHype
Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarios—0
Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks—0
State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning—0
sudo rm -rf agentic_securityCode1
ImF: Implicit Fingerprint for Large Language Models—0
Bitstream Collisions in Neural Image Compression via Adversarial PerturbationsCode0
Make the Most of Everything: Further Considerations on Disrupting Diffusion-based Customization—0
Augmented Adversarial Trigger Learning—0
CyberLLMInstruct: A New Dataset for Analysing Safety of Fine-Tuned LLMs Using Cyber Security DataCode1
ReLATE: Resilient Learner Selection for Multivariate Time-Series Classification Against Adversarial Attacks—0
Scale-Invariant Adversarial Attack against Arbitrary-scale Super-resolution—0
Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate GradientsCode0
Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal—0
Data-free Universal Adversarial Perturbation with Pseudo-semantic PriorCode1
QFAL: Quantum Federated Adversarial Learning—0
Prompt-driven Transferable Adversarial Attack on Person Re-Identification with Attribute-aware Textual Inversion—0
Snowball Adversarial Attack on Traffic Sign Classification—0
XSS Adversarial Attacks Based on Deep Reinforcement Learning: A Replication and Extension StudyCode0
Improving the Transferability of Adversarial Examples by Inverse Knowledge Distillation—0
VGFL-SA: Vertical Graph Federated Learning Structure Attack Based on Contrastive Learning—0
Emoti-Attack: Zero-Perturbation Adversarial Attacks on NLP Systems via Emoji Sequences—0
Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images—0
A Multi-Scale Isolation Forest Approach for Real-Time Detection and Filtering of FGSM Adversarial Attacks in Video Streams of Autonomous Vehicles—0
Moshi Moshi? A Model Selection Hijacking Adversarial Attack—0
Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial TrainingCode1
Show:102550
← PrevPage 4 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