Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 4 de 4
Filtrar
Más filtros












Base de datos
Intervalo de año de publicación
1.
Neural Netw ; 167: 266-282, 2023 Oct.
Artículo en Inglés | MEDLINE | ID: mdl-37666185

RESUMEN

Adversarial robustness is considered a required property of deep neural networks. In this study, we discover that adversarially trained models might have significantly different characteristics in terms of margin and smoothness, even though they show similar robustness. Inspired by the observation, we investigate the effect of different regularizers and discover the negative effect of the smoothness regularizer on maximizing the margin. Based on the analyses, we propose a new method called bridged adversarial training that mitigates the negative effect by bridging the gap between clean and adversarial examples. We provide theoretical and empirical evidence that the proposed method provides stable and better robustness, especially for large perturbations.


Asunto(s)
Redes Neurales de la Computación
2.
IEEE Trans Pattern Anal Mach Intell ; 45(2): 2645-2651, 2023 Feb.
Artículo en Inglés | MEDLINE | ID: mdl-35446760

RESUMEN

Deep learning is vulnerable to adversarial examples. Many defenses based on randomized neural networks have been proposed to solve the problem, but fail to achieve robustness against attacks using proxy gradients such as the Expectation over Transformation (EOT) attack. We investigate the effect of the adversarial attacks using proxy gradients on randomized neural networks and demonstrate that it highly relies on the directional distribution of the loss gradients of the randomized neural network. We show in particular that proxy gradients are less effective when the gradients are more scattered. To this end, we propose Gradient Diversity (GradDiv) regularizations that minimize the concentration of the gradients to build a robust randomized neural network. Our experiments on MNIST, CIFAR10, and STL10 show that our proposed GradDiv regularizations improve the adversarial robustness of randomized neural networks against a variety of state-of-the-art attack methods. Moreover, our method efficiently reduces the transferability among sample models of randomized neural networks.

3.
Sci Rep ; 9(1): 12461, 2019 08 28.
Artículo en Inglés | MEDLINE | ID: mdl-31462658

RESUMEN

In this study, we isolated a total of 238 culturable putative bacterial endophytes from four Pinus species (Pinus densiflora, P. koraiensis, P. rigida, and P. thunbergii) across 18 sampling sites in Korea. The samples were cultured in de Man Rogosa Sharpe and humic acid-vitamin agar media. These selective media were used to isolate lactic acid bacteria and Actinobacteria, respectively. Analysis using 16S ribosomal DNA sequencing grouped the isolated putative bacterial endophytes into 107 operational taxonomic units (OTUs) belonging to 48 genera. Gamma-proteobacteria were the most abundant bacteria in each sampling site and three tissues (needle, stem and root). The highest OTU richness and diversity indices were observed in the roots, followed by stem and needle tissues. Total metabolites extracted from three isolates (two isolates of Escherichia coli and Serratia marcescens) showed significant nematicidal activity against the pine wood nematode (Bursaphelenchus xylophilus). Our findings demonstrated the potential use of bacterial endophytes from pine trees as alternative biocontrol agents against pine wood nematodes.


Asunto(s)
Antinematodos/metabolismo , Bacterias , Biodiversidad , Endófitos , Nematodos/crecimiento & desarrollo , Pinus , Enfermedades de las Plantas/parasitología , Animales , Bacterias/clasificación , Bacterias/metabolismo , Endófitos/clasificación , Endófitos/metabolismo , Pinus/microbiología , Pinus/parasitología , República de Corea
4.
J Ginseng Res ; 43(3): 408-420, 2019 Jul.
Artículo en Inglés | MEDLINE | ID: mdl-31308813

RESUMEN

BACKGROUND: Ginseng (Panax ginseng Meyer) is an invaluable medicinal plant containing various bioactive metabolites (e.g., ginsenosides). Owing to its long cultivation period, ginseng is vulnerable to various biotic constraints. Biological control using endophytes is an important alternative to chemical control. METHODS: In this study, endophytic Trichoderma citrinoviride PG87, isolated from mountain-cultivated ginseng, was evaluated for biocontrol activity against six major ginseng pathogens. T. citrinoviride exhibited antagonistic activity with mycoparasitism against all ginseng pathogens, with high endo-1,4-ß-D-glucanase activity. RESULTS: T. citrinoviride inoculation significantly reduced the disease symptoms caused by Botrytis cinerea and Cylindrocarpon destructans and induced ginsenoside biosynthesis in ginseng plants. T. citrinoviride was formulated as dustable powder and granules. The formulated agents also exhibited significant biocontrol activity and induced ginsenosides production in the controlled environment and mountain area. CONCLUSION: Our results revealed that T. citrinoviride has great potential as a biological control agent and elicitor of ginsenoside production.

SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA
...