Excerpts of professional vocabulary from individual reading papers
A
Attention
- Attention mechanisms : attention machine
- Self-attention
Artificial Neural Networks : Artificial Neural Networks
Adversarial Network : against the network
adversarial examples : adversarial examples
adversarial samples : Adversarial samples
annotation : annotation, comment
authentication : authentication
B
blockchain : blockchain
backward propagation : backpropagation
- backpropagation
- forward propagation: forward propagation
blackbox : black box
Think of the system as a black box, you don't need to know how to implement it internally, you only need to know the input and expected output.
binary : binary
back-propagation : backpropagation
Bluetooth : Bluetooth
C
convolution : Convolution
- Convolutional Neural Network (CNN)
classification : classification
contrastive learning : Contrastive learning
cipher : password
- ciphertext: cipherbook
code
- Encoders: Encoders
- Decoders: decoders
correct : correct, correct
D
detection : detection
- object detection: target detection
distillation : distillation
discriminative : discrimination
- discriminative task: discrimination task
deblurring : deblurring
domain : domain
Data Augmentation : data enhancement
downsampled : downsampling
decision tree : decision tree
Differential privacy (DP) , the gold standard for privacy protection, is considered an effective approach to defend against inference attacks. It requires that the privacy algorithms ensure that changes in individual records have little impact on the analysis results. Since DP guarantees that analyzers have difficulty distinguishing whether a given record is in datasets.
E
Ensemble Learning : integrated learning
explanation techniques : explanation techniques
F
feasibility : feasibility
fidelity : loyalty, faithfulness; verisimilitude; fidelity; conscientiousness, accuracy
Federated Learning : Federated Learning
Fully-connected layers (FC) : fully connected layer
Feed Forward Neural Network (FFN) : Feedforward Neural Network
G
Generative Adversarial Networks (GANs) : Generative Adversarial Networks
gradient descent : Gradient descent
feed-forward : feed forward
H
hyper-parameter : hyperparameters
hierarchical learning : hierarchical learning
**hacker**: Hacker
I
interpretability : interpretability
identification : identity authentication
Inference attack, which aims to infer private information from data analysis tasks, is a significant threat to privacy-preserving data analysis. Many kinds of inference attacks have been proposed, such as Membership Inference Attacks (MIAs) , attribute inference attacks, and category inference attacks.
J
K
L
Linear regression : linear regression
M
multi- : a large number, many
module : module, component
malware : n. malicious software; malicious software. Malware is a synthetic form of malicious software; rogue software
matrix : matrix
memory : memory, memory
METHODOLOGY (methodology) : methodology
Membership inference attacks are familiar attacks on training samples in machine learning. It aims to infer whether a record is a training sample or not.
N
neuron : neuron
natural language processing (NLP)
O
P
pooling : pooling
pixel : pixel
parallel : parallel
proof-of-concept : proof of concept
pricacy protection : privacy protection
probability density function (PDF) : probability density function
Q
R
Recurrent : loop, recursion
- Deep Recurrent Neural Networks: Deep Recurrent Neural Networks
reinforcement learning : reinforcement learning
recognition : recognition
- object recognition: object recognition
- facial recognition
- biometric recognition
Regularized : Regularized
- Regularized iterative algorithms: Regularized iterative algorithms
robustness : Robustness
resolution : resolution
Randomized Response : random response, a method commonly used in differential privacy
S
state-of-the-art : using the most advanced technology; embodying the highest level
sub-field : sub-field
semi : half
supervise : supervision
- supervised learning
- semi-supervised : semi-supervised
- unsupervised
semantic textual similarity (STS) : semantic textual similarity
Semantic Segmentation : Semantic Segmentation++
sensor : sensor
Stream Prefix : The stream prefix refers to the prefix part in a data stream, that is, all the data from the beginning of the stream to a certain position. For example, if a data stream contains the sequence of elements {1, 2, 3, 4, 5}, the prefixes of the data stream can be {1}, {1, 2}, {1, 2, 3}, {1, 2, 3, 4} or {1, 2, 3, 4, 5}.
T
TECH REPORT (tech report) : technical report
Transformer : deformer
token : token, token
- tokenize: Tokenization
- tokenizer: token parser
- Token Enbedding
transparency : transparency
V
vector : vector
validate : validate