Results 71 to 80 of about 14,798 (256)
Adversarial Security Attacks and Perturbations on Machine Learning and Deep Learning Methods [PDF]
, 2019 Arif Siddiqi
openalex +1 more source
Propellants, Explosives, Pyrotechnics, EarlyView.Flowchart the Convolutional Graph Neural Network framework for predicting critical impact velocity in heterogeneous PBX‐9501: A) Initial configurations of three PBX 9501 samples with varying pore structure. B) Generated graph representation for each sample, with nodes positioned at each pore and edges connecting all pores.
Roberto Perera +4 more
wiley +1 more source
Increasing the Robustness of Image Quality Assessment Models Through Adversarial Training
TechnologiesThe adversarial robustness of image quality assessment (IQA) models to adversarial attacks is emerging as a critical issue. Adversarial training has been widely used to improve the robustness of neural networks to adversarial attacks, but little in-depth
Anna Chistyakova +6 more
doaj +1 more source
Dynamics-aware Adversarial Attack of 3D Sparse Convolution Network [PDF]
, 2021 Tao An +7 more
openalex +1 more source
Informatika, 2019 This paper addresses the problem of dependence of the success rate of adversarial attacks to the deep neural networks on the biomedical image type and control parameters of generation of adversarial examples.
D. M. Voynov, V. A. Kovalev
doaj
Statistical Complexity of Quantum Learning
Advanced Quantum Technologies, EarlyView.The statistical performance of quantum learning is investigated as a function of the number of training data N$N$, and of the number of copies available for each quantum state in the training and testing data sets, respectively S$S$ and V$V$. Indeed, the biggest difference in quantum learning comes from the destructive nature of quantum measurements ...
Leonardo Banchi +3 more
wiley +1 more source
Enhancing Adversarial Defense via Brain Activity Integration Without Adversarial Examples
SensorsAdversarial attacks on large-scale vision–language foundation models, such as the contrastive language–image pretraining (CLIP) model, can significantly degrade performance across various tasks by generating adversarial examples that are ...
Tasuku Nakajima +4 more
doaj +1 more source
Quantum‐Noise‐Driven Generative Diffusion Models
Advanced Quantum Technologies, EarlyView.Diffusion Models (DMs) are today a very popular class of generative models for Machine Learning (ML), using a noisy dynamics to learn an unknown density probability of a finite set of samples in order to generate new synthetic data. This study proposes a method to generalize them into the quantum domain by introducing and investigating what are termed ...
Marco Parigi +2 more
wiley +1 more source
CycleGAN-Gradient Penalty for Enhancing Android Adversarial Malware Detection in Gray Box Setting
IEEE AccessAdversarial attacks pose significant threats to Android malware detection by undermining the effectiveness of machine learning-based systems. The rapid increase in Android apps complicates the management of malicious software that can compromise user ...
Fabrice Setephin Atedjio +4 more
doaj +1 more source
Method for Noise‐Induced Regularization in Quantum Neural Networks
Advanced Quantum Technologies, EarlyView.Controllable decoherence is proposed to be used as a regulariser for quantum neural networks. Tuning amplitude, phase, and depolarising noise strengths as hyperparameters can result in minimizing validation error during training. Hardware‐realistic noisy simulation of IBM's Kingston processor shows that inserting controllable idle intervals can achieve
Viacheslav Kuzmin +3 more
wiley +1 more source