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 151–200 of 1808 papers

TitleStatusHype
Robustness-aware Automatic Prompt OptimizationCode0
Retention Score: Quantifying Jailbreak Risks for Vision Language Models—0
Preventing Non-intrusive Load Monitoring Privacy Invasion: A Precise Adversarial Attack Scheme for Networked Smart Meters—0
ErasableMask: A Robust and Erasable Privacy Protection Scheme against Black-box Face Recognition Models—0
PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation—0
Adversarial Attack Against Images Classification based on Generative Adversarial Networks—0
Adversarial Robustness through Dynamic Ensemble Learning—0
Watertox: The Art of Simplicity in Universal Attacks A Cross-Model Framework for Robust Adversarial Generation—0
Physics-Based Adversarial Attack on Near-Infrared Human Detector for Nighttime Surveillance Camera SystemsCode1
Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan ScriptCode1
Adversarially robust generalization theory via Jacobian regularization for deep neural networks—0
Unpacking the Resilience of SNLI Contradiction Examples to AttacksCode0
RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors—0
A2RNet: Adversarial Attack Resilient Network for Robust Infrared and Visible Image FusionCode1
Adversarial Vulnerabilities in Large Language Models for Time Series ForecastingCode1
Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language ModelsCode1
AHSG: Adversarial Attack on High-level Semantics in Graph Neural Networks—0
A Generative Victim Model for Segmentation—0
Take Fake as Real: Realistic-like Robust Black-box Adversarial Attack to Evade AIGC Detection—0
From Flexibility to Manipulation: The Slippery Slope of XAI EvaluationCode0
Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies—0
Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?—0
Hijacking Vision-and-Language Navigation Agents with Adversarial Environmental Attacks—0
Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan ScriptCode0
Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language ModelCode0
Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face DetectionCode1
Intermediate Outputs Are More Sensitive Than You Think—0
Fall Leaf Adversarial Attack on Traffic Sign Classification—0
Visual Adversarial Attack on Vision-Language Models for Autonomous Driving—0
Scaling Laws for Black box Adversarial Attacks—0
Privacy Protection in Personalized Diffusion Models via Targeted Cross-Attention Adversarial Attack—0
Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation—0
Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense—0
NMT-Obfuscator Attack: Ignore a sentence in translation with only one wordCode0
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning—0
BEARD: Benchmarking the Adversarial Robustness for Dataset DistillationCode0
Robust Optimal Power Flow Against Adversarial Attacks: A Tri-Level Optimization Approach—0
Chain Association-based Attacking and Shielding Natural Language Processing Systems—0
Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models—0
Attention Masks Help Adversarial Attacks to Bypass Safety DetectorsCode0
Neural Fingerprints for Adversarial Attack DetectionCode0
Query-Efficient Adversarial Attack Against Vertical Federated Graph LearningCode0
Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language AttackCode1
LiDAttack: Robust Black-box Attack on LiDAR-based Object DetectionCode0
Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models—0
Pseudo-Conversation Injection for LLM Goal Hijacking—0
Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System—0
Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers—0
Evaluating the Robustness of LiDAR Point Cloud Tracking Against Adversarial Attack—0
Generative Adversarial Patches for Physical Attacks on Cross-Modal Pedestrian Re-Identification—0
Show:102550
← PrevPage 4 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