A survey of android malware detection with deep neural models
Deep Learning (DL) is a disruptive technology that has changed the landscape of cyber
security research. Deep learning models have many advantages over traditional Machine …
security research. Deep learning models have many advantages over traditional Machine …
Deep and broad URL feature mining for android malware detection
In recent years, the scale and diversity of malicious software on mobile networks have grown
significantly, thereby causing considerable danger to users' property and personal privacy …
significantly, thereby causing considerable danger to users' property and personal privacy …
Training a Tucker Model With Shared Factors: a Riemannian Optimization Approach
I Peshekhonov, A Arzhantsev… - … Conference on Artificial …, 2024 - proceedings.mlr.press
Factorization of a matrix into a product of two rectangular factors, is a classic tool in various
machine learning applications. Tensor factorizations generalize this concept to more than …
machine learning applications. Tensor factorizations generalize this concept to more than …
Deep and broad learning based detection of android malware via network traffic
In recent years, the scale and diversity of malicious software on mobile networks are
constantly increasing, thereby causing considerable danger to users' property and personal …
constantly increasing, thereby causing considerable danger to users' property and personal …
Revisiting skip-gram negative sampling model with rectification
C Mu, G Yang, Y Zheng - Intelligent Computing: Proceedings of the 2019 …, 2019 - Springer
We revisit skip-gram negative sampling (SGNS), one of the most popular neural-network
based approaches to learning distributed word representation. We first point out the …
based approaches to learning distributed word representation. We first point out the …
Rotations and interpretability of word embeddings: The case of the Russian language
A Zobnin - Analysis of Images, Social Networks and Texts: 6th …, 2018 - Springer
Consider a continuous word embedding model. Usually, the cosines between word vectors
are used as a measure of similarity of words. These cosines do not change under …
are used as a measure of similarity of words. These cosines do not change under …
Investigating the Effectiveness of Whitening Post-processing Methods on Modifying LLMs Representations
Z Wang, Y Wu - 2023 IEEE 35th International Conference on …, 2023 - ieeexplore.ieee.org
In contemporary natural language processing (NLP) tasks, it is common to utilize the
representation of large language models (LLMs) directly in downstream applications …
representation of large language models (LLMs) directly in downstream applications …
Seeds: Sampling-enhanced embeddings
N Gong, N Yao, S Guo - IEEE Transactions on Neural …, 2020 - ieeexplore.ieee.org
Finding a desirable sampling estimator has a profound impact on the development of static
word embedding models, such as continue-bag-of-words (CBOW) and skip gram (SG) …
word embedding models, such as continue-bag-of-words (CBOW) and skip gram (SG) …
Changing the Geometry of Representations: α-Embeddings for NLP Tasks
Word embeddings based on a conditional model are commonly used in Natural Language
Processing (NLP) tasks to embed the words of a dictionary in a low dimensional linear …
Processing (NLP) tasks to embed the words of a dictionary in a low dimensional linear …