Effectiveness of the Execution and Prevention of Metric-Based Adversarial Attacks on Social Network Data <sup>†</sup>
Observed social networks are often considered as proxies for underlying social networks. The analysis of observed networks oftentimes involves the identification of influential nodes via various centrality measures. This paper brings insights from research on adversarial attacks on machine learning...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/11/6/306 |
| _version_ | 1797565926140280832 |
|---|---|
| author | Nikolaus Nova Parulian Tiffany Lu Shubhanshu Mishra Mihai Avram Jana Diesner |
| author_facet | Nikolaus Nova Parulian Tiffany Lu Shubhanshu Mishra Mihai Avram Jana Diesner |
| author_sort | Nikolaus Nova Parulian |
| collection | DOAJ |
| description | Observed social networks are often considered as proxies for underlying social networks. The analysis of observed networks oftentimes involves the identification of influential nodes via various centrality measures. This paper brings insights from research on adversarial attacks on machine learning systems to the domain of social networks by studying strategies by which an adversary can minimally perturb the observed network structure to achieve their target function of modifying the ranking of a target node according to centrality measures. This can represent the attempt of an adversary to boost or demote the degree to which others perceive individual nodes as influential or powerful. We study the impact of adversarial attacks on targets and victims, and identify metric-based security strategies to mitigate such attacks. We conduct a series of controlled experiments on synthetic network data to identify attacks that allow the adversary to achieve their objective with a single move. We then replicate the experiments with empirical network data. We run our experiments on common network topologies and use common centrality measures. We identify a small set of moves that result in the adversary achieving their objective. This set is smaller for decreasing centrality measures than for increasing them. For both synthetic and empirical networks, we observe that larger networks are less prone to adversarial attacks than smaller ones. Adversarial moves have a higher impact on cellular and small-world networks, while random and scale-free networks are harder to perturb. Also, empirical networks are harder to attack than synthetic networks. Using correlation analysis on our experimental results, we identify how combining measures with low correlation can aid in reducing the effectiveness of adversarial moves. Our results also advance the knowledge about the robustness of centrality measures to network perturbations. The notion of changing social network data to yield adversarial outcomes has practical implications, e.g., for information diffusion on social media, influence and power dynamics in social systems, and developing solutions to improving network security. |
| first_indexed | 2024-03-10T19:19:48Z |
| format | Article |
| id | doaj.art-5924f93ada614ecb9f97338e93e0daa2 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-10T19:19:48Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-5924f93ada614ecb9f97338e93e0daa22023-11-20T03:02:47ZengMDPI AGInformation2078-24892020-06-0111630610.3390/info11060306Effectiveness of the Execution and Prevention of Metric-Based Adversarial Attacks on Social Network Data <sup>†</sup>Nikolaus Nova Parulian0Tiffany Lu1Shubhanshu Mishra2Mihai Avram3Jana Diesner4School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL 61820, USASchool of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL 61820, USASchool of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL 61820, USASchool of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL 61820, USASchool of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL 61820, USAObserved social networks are often considered as proxies for underlying social networks. The analysis of observed networks oftentimes involves the identification of influential nodes via various centrality measures. This paper brings insights from research on adversarial attacks on machine learning systems to the domain of social networks by studying strategies by which an adversary can minimally perturb the observed network structure to achieve their target function of modifying the ranking of a target node according to centrality measures. This can represent the attempt of an adversary to boost or demote the degree to which others perceive individual nodes as influential or powerful. We study the impact of adversarial attacks on targets and victims, and identify metric-based security strategies to mitigate such attacks. We conduct a series of controlled experiments on synthetic network data to identify attacks that allow the adversary to achieve their objective with a single move. We then replicate the experiments with empirical network data. We run our experiments on common network topologies and use common centrality measures. We identify a small set of moves that result in the adversary achieving their objective. This set is smaller for decreasing centrality measures than for increasing them. For both synthetic and empirical networks, we observe that larger networks are less prone to adversarial attacks than smaller ones. Adversarial moves have a higher impact on cellular and small-world networks, while random and scale-free networks are harder to perturb. Also, empirical networks are harder to attack than synthetic networks. Using correlation analysis on our experimental results, we identify how combining measures with low correlation can aid in reducing the effectiveness of adversarial moves. Our results also advance the knowledge about the robustness of centrality measures to network perturbations. The notion of changing social network data to yield adversarial outcomes has practical implications, e.g., for information diffusion on social media, influence and power dynamics in social systems, and developing solutions to improving network security.https://www.mdpi.com/2078-2489/11/6/306social network analysisadversarial attacksnetwork robustnesscentrality measures |
| spellingShingle | Nikolaus Nova Parulian Tiffany Lu Shubhanshu Mishra Mihai Avram Jana Diesner Effectiveness of the Execution and Prevention of Metric-Based Adversarial Attacks on Social Network Data <sup>†</sup> Information social network analysis adversarial attacks network robustness centrality measures |
| title | Effectiveness of the Execution and Prevention of Metric-Based Adversarial Attacks on Social Network Data <sup>†</sup> |
| title_full | Effectiveness of the Execution and Prevention of Metric-Based Adversarial Attacks on Social Network Data <sup>†</sup> |
| title_fullStr | Effectiveness of the Execution and Prevention of Metric-Based Adversarial Attacks on Social Network Data <sup>†</sup> |
| title_full_unstemmed | Effectiveness of the Execution and Prevention of Metric-Based Adversarial Attacks on Social Network Data <sup>†</sup> |
| title_short | Effectiveness of the Execution and Prevention of Metric-Based Adversarial Attacks on Social Network Data <sup>†</sup> |
| title_sort | effectiveness of the execution and prevention of metric based adversarial attacks on social network data sup † sup |
| topic | social network analysis adversarial attacks network robustness centrality measures |
| url | https://www.mdpi.com/2078-2489/11/6/306 |
| work_keys_str_mv | AT nikolausnovaparulian effectivenessoftheexecutionandpreventionofmetricbasedadversarialattacksonsocialnetworkdatasupsup AT tiffanylu effectivenessoftheexecutionandpreventionofmetricbasedadversarialattacksonsocialnetworkdatasupsup AT shubhanshumishra effectivenessoftheexecutionandpreventionofmetricbasedadversarialattacksonsocialnetworkdatasupsup AT mihaiavram effectivenessoftheexecutionandpreventionofmetricbasedadversarialattacksonsocialnetworkdatasupsup AT janadiesner effectivenessoftheexecutionandpreventionofmetricbasedadversarialattacksonsocialnetworkdatasupsup |