Skip to Main Content Area
CPS-VO
Contact Support
Browse
Calendar
Announcements
Repositories
Groups
Search
Search for Content
Search for a Group
Search for People
Search for a Project
Tagcloud
› Go to login screen
Not a member?
Click here to register!
Forgot username or password?
Cyber-Physical Systems Virtual Organization
Read-only archive of site from September 29, 2023.
CPS-VO
convolutional networks
biblio
On the Geometry of Rectifier Convolutional Neural Networks
Submitted by grigby1 on Mon, 10/05/2020 - 12:49pm
Geometry
understanding
trained rectifier networks
Tensile stress
rectifier convolutional neural networks
pubcrawl
preimage
preactivation space
natural data
learning (artificial intelligence)
Kernel
inductive bias
gradient descent
Compositionality
deep learning
convolutional neural networks
convolutional neural nets
convolutional networks
convolutional layers
Convolutional codes
convolution
computer vision
Complexity theory
Computing Theory and Compositionality
Human Factors
Human behavior
biblio
Defense Against Adversarial Images Using Web-Scale Nearest-Neighbor Search
Submitted by grigby1 on Fri, 05/22/2020 - 1:34pm
adversarial image
Web-scale nearest-neighbor search
Web-scale image database
Visual Reasoning
visual databases
representation learning
nearest-neighbor defense settings
Large Scale Methods
ImageNet
image representation
image manifold
Datasets and Evaluation
data distribution
security of data
nearest neighbor search
convolutional networks
adversarial perturbations
nearest neighbour methods
Measurement
Metrics
deep learning
Big Data
internet
pubcrawl
convolutional neural nets
biblio
Feature Denoising for Improving Adversarial Robustness
Submitted by grigby1 on Fri, 04/17/2020 - 9:58am
image classification systems
White Box Security
security of data
retrieval
Resiliency
resilience
Recognition: Detection
pubcrawl
pattern classification
nonlocal means
network architectures
Metrics
learning (artificial intelligence)
Iterative methods
image denoising
10-iteration PGD white-box attacks
image classification
feature extraction
feature denoising
deep learning
convolutional networks
Compositionality
composability
categorization
black-box attack settings
Adversarial training
Adversarial robustness
adversarial perturbations
adversarial attacks
2000-iteration PGD white-box attacks
biblio
Empowering convolutional networks for malware classification and analysis
Submitted by grigby1 on Tue, 01/23/2018 - 2:53pm
pattern classification
malware
Malware Analysis
malware analytics
malware classification
malware families
metadata
Metrics
Neural networks
malicious executable detection
PE files
portable executable files
privacy
pubcrawl
Resiliency
statistical analysis
statistical machine learning
Feedforward neural networks
convolutional networks
convolutional neural constructs
Data mining
disassembled malicious binary execution sequences
feature extraction
feature plain vectorization
feedforward neural constructs
feedforward neural nets
Convolutional codes
hierarchical feature extraction
Human behavior
information feature extraction
instruction n-grams convolution
invasive software
learning (artificial intelligence)
malicious executable classification
