Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

My Brother Helps Me: Node Injection Based Adversarial Attack on Social Bot Detection (2310.07159v1)

Published 11 Oct 2023 in cs.CR and cs.SI

Abstract: Social platforms such as Twitter are under siege from a multitude of fraudulent users. In response, social bot detection tasks have been developed to identify such fake 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. In this study, we propose a node injection-based adversarial attack method designed to deceive bot detection models. Notably, neither the target bot nor the newly injected bot can be detected when a new bot is added around the target bot. This attack operates in a black-box fashion, implying that any information related to the victim model remains unknown. To our knowledge, this is the first study exploring the resilience of bot detection through graph node injection. Furthermore, we develop an attribute recovery module to revert the injected node embedding from the graph embedding space back to the original feature space, enabling the adversary to manipulate node perturbation effectively. We conduct adversarial attacks on four commonly used GNN structures for bot detection on two widely used datasets: Cresci-2015 and TwiBot-22. The attack success rate is over 73\% and the rate of newly injected nodes being detected as bots is below 13\% on these two datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Jonathon M Berger and Jonathon Morgan. 2015. The ISIS Twitter Census: Defining and describing the population of ISIS supporters on Twitter. (2015).
  2. Aleksandar Bojchevski and Stephan Günnemann. 2019. Adversarial Attacks on Node Embeddings via Graph Poisoning. In ICML, Vol. 97. 695–704.
  3. Detecting Social Bots by Jointly Modeling Deep Behavior and Content Information. In CIKM. 1995–1998.
  4. Popularity Prediction on Social Platforms with Coupled Graph Neural Networks. In WSDM. 70–78.
  5. Scalable Whitebox Attacks on Tree-based Models. CoRR (2022).
  6. A Survey of Adversarial Learning on Graphs. CoRR (2020).
  7. Title-and-Tag Contrastive Vision-and-Language Transformer for Social Media Popularity Prediction. In ACM MM. 7008–7012.
  8. Fame for sale: Efficient detection of fake Twitter followers. Decision Support Systems 80 (2015), 56–71.
  9. Adversarial Attack on Graph Structured Data. In ICML, Vol. 80. 1123–1132.
  10. Perils and Challenges of Social Media and Election Manipulation Analysis: The 2018 US Midterms. In WWW. 237–247.
  11. Detecting Bots in Social-networks using Node and Structural Embeddings. In DATA. 50–61.
  12. TwiBot-22: Towards Graph-Based Twitter Bot Detection. CoRR (2022).
  13. SATAR: A Self-supervised Approach to Twitter Account Representation Learning and its Application in Bot Detection. In CIKM. 3808–3817.
  14. BotRGCN: Twitter bot detection with relational graph convolutional networks. In ASONAM. 236–239.
  15. Emilio Ferrara. 2017. Disinformation and social bot operations in the run up to the 2017 French presidential election. First Monday 22, 8 (2017).
  16. Emilio Ferrara. 2020. What types of COVID-19 conspiracies are populated by Twitter bots? First Monday 25, 6 (2020).
  17. HyperAttack: Multi-Gradient-Guided White-box Adversarial Structure Attack of Hypergraph Neural Networks. CoRR (2023).
  18. Heterogeneous Graph Transformer. In WWW. 2704–2710.
  19. Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing. In WWW. 2718–2724.
  20. Exploring adversarial attacks and defences for fake twitter account detection. Technologies 8, 4 (2020), 64.
  21. Political astroturfing on Twitter: How to coordinate a disinformation campaign. Political communication 37, 2 (2020), 256–280.
  22. Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR.
  23. Jürgen Knauth. 2019. Language-Agnostic Twitter-Bot Detection. In RANLP. 550–558.
  24. Sneha Kudugunta and Emilio Ferrara. 2018. Deep neural networks for bot detection. Information Sciences 467 (2018), 312–322.
  25. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR (2019).
  26. Are we really making much progress?: Revisiting, benchmarking and refining heterogeneous graph neural networks. In KDD. 1150–1160.
  27. Towards More Practical Adversarial Attacks on Graph Neural Networks. In NeurIPS.
  28. Graph Adversarial Attack via Rewiring. In KDD. 1161–1169.
  29. Bot2Vec: A general approach of intra-community oriented representation learning for bot detection in different types of social networks. Information Systems 103 (2022), 101771.
  30. A Persistent Weisfeiler-Lehman Procedure for Graph Classification. In ICML, Vol. 97. 5448–5458.
  31. Benign Adversarial Attack: Tricking Models for Goodness. In ACM MM. 6883–6889.
  32. Modeling Relational Data with Graph Convolutional Networks. In ESWC, Vol. 10843. 593–607.
  33. Adversarial Attacks on Graph Neural Networks via Node Injections: A Hierarchical Reinforcement Learning Approach. In WWW. 673–683.
  34. An Efficient Multi-View Multimodal Data Processing Framework for Social Media Popularity Prediction. In ACM MM. 7200–7204.
  35. Single Node Injection Attack against Graph Neural Networks. In CIKM. 1794–1803.
  36. Are we secure from bots? Investigating vulnerabilities of botometer. In UBMK. 343–348.
  37. Helping Users Tackle Algorithmic Threats on Social Media: A Multimedia Research Agenda. In ACM MM. 4425–4434.
  38. MGAAttack: Toward More Query-efficient Black-box Attack by Microbial Genetic Algorithm. In ACM MM. 2229–2236.
  39. Graph Convolutional Networks using Heat Kernel for Semi-supervised Learning. In IJCAI. 1928–1934.
  40. Adversarial Attacks and Defenses in Images, Graphs and Text: A Review. Int. J. Autom. Comput. 17, 2 (2020), 151–178.
  41. Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective. In IJCAI. 3961–3967.
  42. Towards Feature Space Adversarial Attack by Style Perturbation. In AAAI. 10523–10531.
  43. Learning Optimization-based Adversarial Perturbations for Attacking Sequential Recognition Models. In ACM MM. 2802–2822.
  44. Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness. CoRR (2021).
  45. Meta Gradient Adversarial Attack. In ICCV. 7728–7737.
  46. Adversarial Attacks on Neural Networks for Graph Data. In IJCAI. 6246–6250.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now