MulBot: Unsupervised Bot Detection Based on Multivariate Time Series

• URL: http://arxiv.org/abs/2209.10361v1
• Date: Wed, 21 Sep 2022 13:56:12 GMT
• Title: MulBot: Unsupervised Bot Detection Based on Multivariate Time Series
• Authors: Lorenzo Mannocci, Stefano Cresci, Anna Monreale, Athina Vakali, Maurizio Tesconi
• Abstract summary: MulBot is an unsupervised bot detector based on multidimensional temporal features extracted from user timelines. We perform a binary classification task achieving f1-score $= 0.99$, outperforming state-of-the-art methods. We also demonstrate MulBot's strengths in a novel and practically-relevant task: detecting and separating different botnets.
• Score: 2.525739800601558
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Online social networks are actively involved in the removal of malicious social bots due to their role in the spread of low quality information. However, most of the existing bot detectors are supervised classifiers incapable of capturing the evolving behavior of sophisticated bots. Here we propose MulBot, an unsupervised bot detector based on multivariate time series (MTS). For the first time, we exploit multidimensional temporal features extracted from user timelines. We manage the multidimensionality with an LSTM autoencoder, which projects the MTS in a suitable latent space. Then, we perform a clustering step on this encoded representation to identify dense groups of very similar users -- a known sign of automation. Finally, we perform a binary classification task achieving f1-score $= 0.99$, outperforming state-of-the-art methods (f1-score $\le 0.97$). Not only does MulBot achieve excellent results in the binary classification task, but we also demonstrate its strengths in a novel and practically-relevant task: detecting and separating different botnets. In this multi-class classification task we achieve f1-score $= 0.96$. We conclude by estimating the importance of the different features used in our model and by evaluating MulBot's capability to generalize to new unseen bots, thus proposing a solution to the generalization deficiencies of supervised bot detectors.

Related papers

• BSG4Bot: Efficient Bot Detection based on Biased Heterogeneous Subgraphs [6.99955702963268]
  The detection of malicious social bots has become a crucial task, as bots can be easily deployed and manipulated to spread disinformation. Most existing approaches utilize graph neural networks (GNNs)to capture both user profle and structural features. This paper proposes a method named BSG4Bot with an intuition that GNNs training on Biased SubGraphs can improve both performance and time/space efficiency in bot detection.
  arXiv  Detail & Related papers  (2024-10-07T15:52:51Z)
• BotSSCL: Social Bot Detection with Self-Supervised Contrastive Learning [6.317191658158437]
  We propose a novel framework for social Bot detection with Self-Supervised Contrastive Learning (BotSSCL) BotSSCL uses contrastive learning to distinguish between social bots and humans in the embedding space to improve linear separability. We demonstrate BotSSCL's robustness against adversarial attempts to manipulate bot accounts to evade detection.
  arXiv  Detail & Related papers  (2024-02-06T06:13:13Z)
• My Brother Helps Me: Node Injection Based Adversarial Attack on Social Bot Detection [69.99192868521564]
  Social platforms such as Twitter are under siege from a multitude of fraudulent users. Due to the structure of social networks, the majority of methods are based on the graph neural network(GNN), which is susceptible to attacks. We propose a node injection-based adversarial attack method designed to deceive bot detection models.
  arXiv  Detail & Related papers  (2023-10-11T03:09:48Z)
• MONDEO: Multistage Botnet Detection [2.259031129687683]
  MONDEO is a multistage mechanism to detect DNS-based botnet malware. It comprises four detection stages: Blacklisting/Whitelisting, Query rate analysis, DGA analysis, and Machine learning evaluation. MONDEO was tested against several datasets to measure its efficiency and performance.
  arXiv  Detail & Related papers  (2023-08-31T09:12:30Z)
• BotShape: A Novel Social Bots Detection Approach via Behavioral Patterns [4.386183132284449]
  Based on a real-world data set, we construct behavioral sequences from raw event logs. We observe differences between bots and genuine users and similar patterns among bot accounts. We present a novel social bot detection system BotShape, to automatically catch behavioral sequences and characteristics.
  arXiv  Detail & Related papers  (2023-03-17T19:03:06Z)
• Identification of Twitter Bots based on an Explainable ML Framework: the US 2020 Elections Case Study [72.61531092316092]
  This paper focuses on the design of a novel system for identifying Twitter bots based on labeled Twitter data. Supervised machine learning (ML) framework is adopted using an Extreme Gradient Boosting (XGBoost) algorithm. Our study also deploys Shapley Additive Explanations (SHAP) for explaining the ML model predictions.
  arXiv  Detail & Related papers  (2021-12-08T14:12:24Z)
• A ground-truth dataset and classification model for detecting bots in GitHub issue and PR comments [70.1864008701113]
  Bots are used in Github repositories to automate repetitive activities that are part of the distributed software development process. This paper proposes a ground-truth dataset, based on a manual analysis with high interrater agreement, of pull request and issue comments in 5,000 distinct Github accounts. We propose an automated classification model to detect bots, taking as main features the number of empty and non-empty comments of each account, the number of comment patterns, and the inequality between comments within comment patterns.
  arXiv  Detail & Related papers  (2020-10-07T09:30:52Z)
• Induction and Exploitation of Subgoal Automata for Reinforcement Learning [75.55324974788475]
  We present ISA, an approach for learning and exploiting subgoals in episodic reinforcement learning (RL) tasks. ISA interleaves reinforcement learning with the induction of a subgoal automaton, an automaton whose edges are labeled by the task's subgoals. A subgoal automaton also consists of two special states: a state indicating the successful completion of the task, and a state indicating that the task has finished without succeeding.
  arXiv  Detail & Related papers  (2020-09-08T16:42:55Z)
• Detection of Novel Social Bots by Ensembles of Specialized Classifiers [60.63582690037839]
  Malicious actors create inauthentic social media accounts controlled in part by algorithms, known as social bots, to disseminate misinformation and agitate online discussion. We show that different types of bots are characterized by different behavioral features. We propose a new supervised learning method that trains classifiers specialized for each class of bots and combines their decisions through the maximum rule.
  arXiv  Detail & Related papers  (2020-06-11T22:59:59Z)
• BeCAPTCHA-Mouse: Synthetic Mouse Trajectories and Improved Bot Detection [78.11535724645702]
  We present BeCAPTCHA-Mouse, a bot detector based on a neuromotor model of mouse dynamics. BeCAPTCHA-Mouse is able to detect bot trajectories of high realism with 93% of accuracy in average using only one mouse trajectory.
  arXiv  Detail & Related papers  (2020-05-02T17:40:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.