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 351–400 of 1808 papers

TitleStatusHype
Tropical Attention: Neural Algorithmic Reasoning for Combinatorial Algorithms—0
Experimental robustness benchmark of quantum neural network on a superconducting quantum processor—0
Chain-of-Thought Poisoning Attacks against R1-based Retrieval-Augmented Generation Systems—0
Beyond Classification: Evaluating Diffusion Denoised Smoothing for Security-Utility Trade off—0
Adverseness vs. Equilibrium: Exploring Graph Adversarial Resilience through Dynamic Equilibrium—0
EVALOOP: Assessing LLM Robustness in Programming from a Self-consistency Perspective—0
FABLE: A Localized, Targeted Adversarial Attack on Weather Forecasting Models—0
Adversarial Attack on Large Language Models using Exponentiated Gradient DescentCode0
Evaluating the Robustness of Adversarial Defenses in Malware Detection SystemsCode0
Towards Adaptive Meta-Gradient Adversarial Examples for Visual TrackingCode0
No Query, No Access—0
Input-Specific and Universal Adversarial Attack Generation for Spiking Neural Networks in the Spiking Domain—0
Adversarial Attacks in Multimodal Systems: A Practitioner's Survey—0
Data-Driven Falsification of Cyber-Physical SystemsCode0
Adversarial Robustness Analysis of Vision-Language Models in Medical Image SegmentationCode0
Rogue Cell: Adversarial Attack and Defense in Untrusted O-RAN Setup Exploiting the Traffic Steering xApp—0
Constrained Network Adversarial Attacks: Validity, Robustness, and Transferability—0
Analysis of the vulnerability of machine learning regression models to adversarial attacks using data from 5G wireless networks—0
AGATE: Stealthy Black-box Watermarking for Multimodal Model Copyright Protection—0
Forging and Removing Latent-Noise Diffusion Watermarks Using a Single ImageCode0
Seeking Flat Minima over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation—0
Hydra: An Agentic Reasoning Approach for Enhancing Adversarial Robustness and Mitigating Hallucinations in Vision-Language Models—0
Adversarial Attack for RGB-Event based Visual Object TrackingCode0
Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation—0
Quantum Computing Supported Adversarial Attack-Resilient Autonomous Vehicle Perception Module for Traffic Sign ClassificationCode0
Towards Safe Synthetic Image Generation On the Web: A Multimodal Robust NSFW Defense and Million Scale DatasetCode0
SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models—0
Bregman Linearized Augmented Lagrangian Method for Nonconvex Constrained Stochastic Zeroth-order Optimization—0
Toward Spiking Neural Network Local Learning Modules Resistant to Adversarial Attacks—0
Towards Calibration Enhanced Network by Inverse Adversarial Attack—0
Secure Diagnostics: Adversarial Robustness Meets Clinical Interpretability—0
Moving Target Defense Against Adversarial False Data Injection Attacks In Power Grids—0
Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation—0
Unleashing the Power of Pre-trained Encoders for Universal Adversarial Attack Detection—0
TenAd: A Tensor-based Low-rank Black Box Adversarial Attack for Video Classification—0
Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarios—0
Agents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks—0
State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning—0
Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks—0
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
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
QFAL: Quantum Federated Adversarial Learning—0
Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal—0
Snowball Adversarial Attack on Traffic Sign Classification—0
Prompt-driven Transferable Adversarial Attack on Person Re-Identification with Attribute-aware Textual Inversion—0
Show:102550
← PrevPage 8 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