natural-language-processing-7

Spam detection

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in spam-detection-7

Trend

Dataset

Best Model

Actions

Traditional and Context-specific Spam Twitter

Libraries

i

Use these libraries to find spam-detection-7 models and implementations

Datasets

Traditional and Context-specific Spam Twitter

ViSpamReviews

Subtasks

Context-specific Spam Detection Traditional Spam Detection

Most implemented papers

Black-Box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers

Jack Lanchantin, Ji Gao, M. Soffa, Yanjun Qi•Fri Jan 12 2018

A novel algorithm is presented, DeepWordBug, to effectively generate small text perturbations in a black-box setting that forces a deep-learning classifier to misclassify a text input.

814

Content

0

Paper Graph

Evading classifiers in discrete domains with provable optimality guarantees

Bogdan Kulynych, C. Troncoso, Jamie Hayes, N. Samarin•Wed Oct 24 2018

A graphical framework that generalizes existing attacks in discrete domains, can accommodate complex cost functions beyond $p-norms, including financial cost incurred when attacking a classifier, and efficiently produces valid adversarial examples with guarantees of minimal adversarial cost is introduced.

21 0

Paper Graph

Stronger data poisoning attacks break data sanitization defenses

Percy Liang, Pang Wei Koh, J. Steinhardt•Thu Nov 01 2018

Three attacks are developed that can bypass a broad range of common data sanitization defenses, including anomaly detectors based on nearest neighbors, training loss, and singular-value decomposition, and the Karush–Kuhn–Tucker conditions.

272 0

Paper Graph

GANs for Semi-Supervised Opinion Spam Detection

Gray Stanton, Athirai Aravazhi Irissappane•Mon Mar 18 2019

This paper proposes spamGAN, a generative adversarial network which relies on limited set of labeled data as well as unlabeled data for opinion spam detection and improves the state-of-the-art GAN based techniques for text classification.

46 0

Paper Graph

Cost-Aware Robust Tree Ensembles for Security Applications

S. Jana, Shiqi Wang, Yizheng Chen, Weifan Jiang, Asaf Cidon•Mon Dec 02 2019

This paper proposes a new cost modeling method to capture the domain knowledge of features as constraint, and then integrates the cost-driven constraint into the node construction process to train robust tree ensembles.

26 0

Paper Graph

Deep convolutional forest: a dynamic deep ensemble approach for spam detection in text

Mai A. Shaaban, Y. F. Hassan, S. Guirguis•Sat Oct 09 2021

A dynamic deep ensemble model for spam detection that adjusts its complexity and extracts features automatically and achieved high precision, recall, f1-score and accuracy of 98.38% is introduced.

45 0

Paper Graph

An Automated Text Categorization Framework based on Hyperparameter Optimization

Eric Sadit Tellez, Daniela Moctezuma, Sabino Miranda-Jiménez, Mario Graff•Wed Apr 05 2017

A minimalistic and wide system able to tackle text classification tasks independent of domain and language, namely microTC is proposed, composed of some easy to implement text transformations, text representations, and a supervised learning algorithm that produces a competitive classifier even in the domain of informally written text.

79 0

Paper Graph

Natural language processing: state of the art, current trends and challenges

Diksha Khurana, Aditya Koli, Kiran Khatter, Sukhdev Singh•Wed Aug 16 2017

This paper discusses in detail the state of the art presenting the various applications of NLP, current trends, and challenges, and presents a discussion on some available datasets, models, and evaluation metrics in NLP.

1390 0

Paper Graph

EMFET: E-mail Features Extraction Tool

Wadi' Hijawi, Hossam Faris, Ja'far Alqatawna, Ibrahim Aljarah, Ala’ M. Al-Zoubi, Maria Habib•Tue Nov 21 2017

The purpose of the tool is to help practitioners and researchers to build datasets that can be used for training machine learning models for spam detection.

5 0

Paper Graph

Adding a benchmark result helps the community track progress.