Results 81 to 90 of about 79,418 (169)

Certified Defenses against Adversarial Examples

, 2018
While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs. Defenses based on regularization and adversarial training have been proposed, but often followed by new, stronger attacks that defeat these defenses. Can we
Raghunathan, Aditi, Steinhardt, Jacob, Liang, Percy   +2 more
openaire   +2 more sources

Adversarial Defense Based on Denoising Convolutional Autoencoder in EEG-Based Brain–Computer Interfaces

IEEE Access
The exploration and implementation of brain-computer interfaces (BCIs) utilizing electro- encephalography (EEG) are becoming increasingly widespread. However, their safety considerations have received scant attention.
Yongting Ding, Lin Li, Qingyan Li
doaj   +1 more source

Traffic adversarial example attack and defense method based on explainable artificial intelligence

Tongxin xuebao
An adversarial example attack method based on XAI was proposed for AI-based NIDS. By identifying critical perturbation features with XAI and applying targeted perturbations while preserving traffic functionality, malicious traffic was gradually altered ...
MA Bowen, GUO Yuanbo, TIAN Jiwei, MA Jun, HU Yongjin   +4 more
doaj  

Research on adversarial attacks and defense performance of image classification models for automated driving systems

机车电传动
Image classification models have been widely applied to facilitate functions such as autonomous perception and positioning for automated driving in many transportation systems, including automobiles, autonomous rail and urban rail transit systems ...
TANG Jun, HUANG Wenjing, LI Shuang, WU Zili   +3 more
doaj  

Adversarial Defense without <i>Adversarial Defense</i>: Enhancing Language Model Robustness via Instance-level Principal Component Removal. [PDF]

Trans Assoc Comput Linguist
Wang Y, Xiao C, Li Y, Middleton SE, Moubayed NA, Lin C.   +5 more
europepmc   +1 more source

An Integrated and Robust Vision System for Internal and External Thread Defect Detection with Adversarial Defense. [PDF]

Sensors (Basel)
Fu L, Li L, Zhang G, Jiang Z.
europepmc   +1 more source

Random heterogeneous spiking neural network for adversarial defense. [PDF]

iScience
Wang J, Zhao D, Du C, He X, Zhang Q, Zeng Y.   +5 more
europepmc   +1 more source

Adversarial robust EEG-based brain-computer interfaces using a hierarchical convolutional neural network. [PDF]

Sci Rep
Samuel J, Murugan TK, Govindaraj L, Balaji M, SenthilKumar V, Sundararajan S.   +5 more
europepmc   +1 more source

STS-AT: A Structured Tensor Flow Adversarial Training Framework for Robust Intrusion Detection. [PDF]

Sensors (Basel)
Zhu J, Chen Z, Cong R, Sun H, Dong Y.
europepmc   +1 more source

Privacy-preserving cyberthreat detection in decentralized social media with federated cross-modal graph transformers. [PDF]

Sci Rep
Premkumar D, Nachimuthu SK.
europepmc   +1 more source