Performance Evaluation of Knowledge Graph Embedding Approaches under Non-adversarial Attacks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909248466714624 |
|---|---|
| author | Kapoor, Sourabh Sharma, Arnab Röder, Michael Demir, Caglar Ngomo, Axel-Cyrille Ngonga |
| author_facet | Kapoor, Sourabh Sharma, Arnab Röder, Michael Demir, Caglar Ngomo, Axel-Cyrille Ngonga |
| contents | Knowledge Graph Embedding (KGE) transforms a discrete Knowledge Graph (KG) into a continuous vector space facilitating its use in various AI-driven applications like Semantic Search, Question Answering, or Recommenders. While KGE approaches are effective in these applications, most existing approaches assume that all information in the given KG is correct. This enables attackers to influence the output of these approaches, e.g., by perturbing the input. Consequently, the robustness of such KGE approaches has to be addressed. Recent work focused on adversarial attacks. However, non-adversarial attacks on all attack surfaces of these approaches have not been thoroughly examined. We close this gap by evaluating the impact of non-adversarial attacks on the performance of 5 state-of-the-art KGE algorithms on 5 datasets with respect to attacks on 3 attack surfaces-graph, parameter, and label perturbation. Our evaluation results suggest that label perturbation has a strong effect on the KGE performance, followed by parameter perturbation with a moderate and graph with a low effect. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_06855 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Performance Evaluation of Knowledge Graph Embedding Approaches under Non-adversarial Attacks Kapoor, Sourabh Sharma, Arnab Röder, Michael Demir, Caglar Ngomo, Axel-Cyrille Ngonga Machine Learning Cryptography and Security Knowledge Graph Embedding (KGE) transforms a discrete Knowledge Graph (KG) into a continuous vector space facilitating its use in various AI-driven applications like Semantic Search, Question Answering, or Recommenders. While KGE approaches are effective in these applications, most existing approaches assume that all information in the given KG is correct. This enables attackers to influence the output of these approaches, e.g., by perturbing the input. Consequently, the robustness of such KGE approaches has to be addressed. Recent work focused on adversarial attacks. However, non-adversarial attacks on all attack surfaces of these approaches have not been thoroughly examined. We close this gap by evaluating the impact of non-adversarial attacks on the performance of 5 state-of-the-art KGE algorithms on 5 datasets with respect to attacks on 3 attack surfaces-graph, parameter, and label perturbation. Our evaluation results suggest that label perturbation has a strong effect on the KGE performance, followed by parameter perturbation with a moderate and graph with a low effect. |
| title | Performance Evaluation of Knowledge Graph Embedding Approaches under Non-adversarial Attacks |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2407.06855 |