Training data

biblio

Estimating the Number of Hidden Nodes of the Single-Hidden-Layer Feedforward Neural Networks

Submitted by grigby1 on Fri, 07/03/2020 - 4:54pm

Artificial Neural Networks
attribute-based data normalization
Compositionality
computer architecture
cyber physical systems
data normalization
decomposition
Eigenvalues and eigenfunctions
feedforward neural nets
Feedforward neural networks
hidden nodes
Metrics
normalized data
optimal number
pubcrawl
sample-based data normalization
single-hidden-layer feedforward neural network
singular value decomposition
Training
Training data

biblio

Preserving Privacy in Convolutional Neural Network: An ∊-tuple Differential Privacy Approach

Submitted by aekwall on Mon, 06/22/2020 - 11:20am

Cloud Computing
Scalability
data privacy
learning (artificial intelligence)
Resiliency
Human behavior
pubcrawl
composability
classification
privacy
CNN
convolutional neural nets
convolutional neural network
image recognition
transfer learning
Deep Neural Network
differential privacy
CNN model
medical data
complex data features
deep neural networks
financial data
model buildup data
model inversion attack
privacy concern
privacy preserving model
reusable output model
salient data features
significant accuracy degradation
Training data
ϵ-tuple differential privacy approach

biblio

Research on Extending Person Re-identification Datasets Based on Generative Adversarial Network

Submitted by grigby1 on Fri, 06/12/2020 - 12:22pm

Cameras
deep learning
deep training
feature extraction
Generative Adversarial Learning
Generative Adversarial Nets
generative adversarial network
generative adversarial networks
Generators
Image color analysis
label smoothing regularization for outliers with weight algorithm
learning (artificial intelligence)
Metrics
neural nets
object detection
pedestrians
pedestrians image
Person Re-ID
Person re-identification
person re-identification datasets
pubcrawl
resilience
Resiliency
Scalability
surveillance camera network
Training
Training data

biblio

Membership Inference Attacks Against Adversarially Robust Deep Learning Models

Submitted by grigby1 on Fri, 04/03/2020 - 12:56pm

deep learning
learning (artificial intelligence)
security of data
Training
Predictive models
security
pubcrawl
Resiliency
data privacy
Data models
privacy
security challenges
neural nets
Metrics
Compositionality
provable security
adversarial defense
adversarial defense methods
adversarial defenses
adversarial training method
adversarially robust deep learning models
empirical membership inference attacks
evasion attacks
membership inference attack
privacy challenges
provable defense
security and privacy
target model
Training data
resilience

biblio

Countermeasure of Lightweight Physical Unclonable Function Against Side-Channel Attack

Submitted by grigby1 on Mon, 03/02/2020 - 1:32pm

authentication
countermeasure method
Cryptography
external Internet
field programmable gate arrays
Hardware Security
Human behavior
Human Factors
Industrial Internet of Things
Integrated circuit modeling
internet
Internet of Things
lightweight physical unclonable function
lightweight PUF
message authentication
Metrics
modeling attack
Physical Unclonable Function
power aware computing
power consumption
Power demand
Power measurement
pubcrawl
Scalability
security of IoT
Side-channel attack
side-channel information
Tamper resistance
Training data

biblio

Ensemble-Learning-Based Hardware Trojans Detection Method by Detecting the Trigger Nets

Submitted by grigby1 on Wed, 02/26/2020 - 4:38pm

cyber physical systems
ensemble learning method
feature extraction
Hardware
hardware-Trojan detection method
IC design phase
IC systems
integrated circuit design
Integrated circuit modeling
learning (artificial intelligence)
pubcrawl
resilience
Resiliency
security
supply chain security
suspicious Trigger nets
Training
Training data
Trigger-net features
Trojan circuits
trojan horse detection
Trojan horses
Trojan types

biblio

Malware Evasion Attack and Defense

Submitted by grigby1 on Tue, 02/18/2020 - 11:53am

adversarial example
adversarial examples
Adversarial Machine Learning
black-box attacks
composability
Data models
defense
defense approaches
Detectors
Evasion Attack
grey-box evasion attacks
invasive software
learning (artificial intelligence)
machine learning classifiers
malware
malware detection systems
malware evasion attack
Metrics
ML classifier
ML-based malware detector
pattern classification
Perturbation methods
pubcrawl
resilience
Resiliency
security
Training
Training data
white box cryptography
White Box Security
white-box evasion attacks

biblio

Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-Box Inference Attacks against Centralized and Federated Learning

Submitted by grigby1 on Tue, 02/18/2020 - 11:52am

active membership inference attacks
active white-box inference attacks
black-box attacks
centralized learning
CIFAR dataset
composability
comprehensive privacy analysis
Computational modeling
Data models
data privacy
deep learning
deep learning models
deep neural networks
Deep-learning
federated learning setting
Federated-Learning
gradient methods
Inference algorithms
inference mechanisms
Inference-Attacks
learning (artificial intelligence)
Membership-Inference
Metrics
neural nets
privacy
privacy leakage
pubcrawl
resilience
Resiliency
stochastic gradient descent algorithm
Stochastic processes
Stochastic-Gradient-Descent
Training
Training data
white box cryptography
White Box Security
white-box membership inference attacks

biblio

Learning Transferable Features For Open-Domain Question Answering

Submitted by aekwall on Mon, 11/25/2019 - 2:01pm

Adaptation models
Analogies and Transference
clustering algorithm
complementary data
Data models
Deep Networks
domain adaptation approaches
domain-adaptation
domain-specific features
domain-specific QA models
Human behavior
Human Factors
information retrieval
Knowledge Discovery
learning (artificial intelligence)
Linear programming
natural language
natural language processing
open-domain QA models
open-domain question answering
open-domain Question-Answering models
pattern clustering
pubcrawl
question answering (information retrieval)
Question-Answering
sentence-level QA models
single open-domain QA model
span-level QA benefits
Task Analysis
Training
training corpora
Training data
transfer learning
transferable feature learning
transferable features

biblio

Chronic Poisoning against Machine Learning Based IDSs Using Edge Pattern Detection

Submitted by grigby1 on Wed, 05/01/2019 - 11:33am

Batch-EPD Boundary Pattern detection algorithm
big data era
chronic poisoning attack
composability
Data models
detection algorithms
edge detection
Edge Pattern Detection algorithm
edge pattern points
Image edge detection
Intrusion Detection
Intrusion Detection Systems
learning (artificial intelligence)
machine learning
machine learning algorithms
Metrics
pubcrawl
resilience
Resiliency
Scalability
security
security of data
security threats
Training data

1
2
3
4
next ›
last »

Cyber-Physical Systems Virtual Organization

Fostering collaboration among CPS professionals in academia, government, and industry

Training data

Estimating the Number of Hidden Nodes of the Single-Hidden-Layer Feedforward Neural Networks

Preserving Privacy in Convolutional Neural Network: An ∊-tuple Differential Privacy Approach

Research on Extending Person Re-identification Datasets Based on Generative Adversarial Network

Membership Inference Attacks Against Adversarially Robust Deep Learning Models

Countermeasure of Lightweight Physical Unclonable Function Against Side-Channel Attack

Ensemble-Learning-Based Hardware Trojans Detection Method by Detecting the Trigger Nets

Malware Evasion Attack and Defense

Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-Box Inference Attacks against Centralized and Federated Learning

Learning Transferable Features For Open-Domain Question Answering

Chronic Poisoning against Machine Learning Based IDSs Using Edge Pattern Detection