Youngja Park
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Youngja Park has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
Ian M. Molloy
IBM T.J. Watson Research Center
2 shared publicationsSuresh N. Chari
IBM T.J. Watson Research Center
2 shared publications- Weiqiu You
University of Pennsylvania Philadelphia PA USA
2 shared publications Chris Gates
Purdue University
1 shared publication- Jatin Arora
Youngja Park IBM T.J. Watson Research Center
1 shared publication Ninghi Li
Purdue University
1 shared publication
Latest Publications
- Open Access
Cyber-Attack Technique Classification Using Two-Stage Trained Large Language Models
Understanding the attack patterns associated with a cyberattack is crucial for comprehending the attacker's behaviors and implementing the right mitigation measures. However, majority of the information regarding new attacks is typically presented in unstructured text, posing significant challenges for security analysts in collecting necessary information. In this paper, we present a sentence classification system that can identify the attack techniques described in natural language sentences from cyber threat intelligence (CTI) reports. We propose a new method for utilizing auxiliary data with the same labels to improve classification for the low-resource cyberattack classification task. The system first trains the model using the augmented training data and then trains more using only the primary data. We validate our model using the TRAM data1 and the MITRE ATT&CK framework. Experiments show that our method enhances Macro-F1 by 5 to 9 percentage points and keeps Micro-F1 scores competitive when compared to the baseline performance on the TRAM dataset.
Open AccessCyber-Attack Technique Classification Using Two-Stage Trained Large Language Models
Understanding the attack patterns associated with a cyberattack is crucial for comprehending the attacker's behaviors and implementing the right mitigation measures. However, majority of the information regarding new attacks is typically presented in unstructured text, posing significant challenges for security analysts in collecting necessary information. In this paper, we present a sentence classification system that can identify the attack techniques described in natural language sentences from cyber threat intelligence (CTI) reports. We propose a new method for utilizing auxiliary data with the same labels to improve classification for the low-resource cyberattack classification task. The system first trains the model using the augmented training data and then trains more using only the primary data. We validate our model using the TRAM data1 and the MITRE ATT&CK framework. Experiments show that our method enhances Macro-F1 by 5 to 9 percentage points and keeps Micro-F1 scores competitive when compared to the baseline performance on the TRAM dataset.
- Open Access
Split-NER: Named Entity Recognition via Two Question-Answering-based Classifications
In this work, we address the NER problem by splitting it into two logical sub-tasks: (1) Span Detection which simply extracts entity mention spans irrespective of entity type; (2) Span Classification which classifies the spans into their entity types. Further, we formulate both sub-tasks as question-answering (QA) problems and produce two leaner models which can be optimized separately for each sub-task. Experiments with four cross-domain datasets demonstrate that this two-step approach is both effective and time efficient. Our system, SplitNER outperforms baselines on OntoNotes5.0, WNUT17 and a cybersecurity dataset and gives on-par performance on BioNLP13CG. In all cases, it achieves a significant reduction in training time compared to its QA baseline counterpart. The effectiveness of our system stems from fine-tuning the BERT model twice, separately for span detection and classification. The source code can be found at https://github.com/c3sr/split-ner.
Open AccessSplit-NER: Named Entity Recognition via Two Question-Answering-based Classifications
In this work, we address the NER problem by splitting it into two logical sub-tasks: (1) Span Detection which simply extracts entity mention spans irrespective of entity type; (2) Span Classification which classifies the spans into their entity types. Further, we formulate both sub-tasks as question-answering (QA) problems and produce two leaner models which can be optimized separately for each sub-task. Experiments with four cross-domain datasets demonstrate that this two-step approach is both effective and time efficient. Our system, SplitNER outperforms baselines on OntoNotes5.0, WNUT17 and a cybersecurity dataset and gives on-par performance on BioNLP13CG. In all cases, it achieves a significant reduction in training time compared to its QA baseline counterpart. The effectiveness of our system stems from fine-tuning the BERT model twice, separately for span detection and classification. The source code can be found at https://github.com/c3sr/split-ner.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 113-122
A Pretrained Language Model for Cyber Threat Intelligence
Youngja Park, Weiqiu You. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 113-122
Open AccessA Pretrained Language Model for Cyber Threat Intelligence
Youngja Park, Weiqiu You. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2023.
- 18 November 2015
- Published by Springer Nature
- p. 396-414
Learning from Others: User Anomaly Detection Using Anomalous Samples from Other Users
- 18 November 2015
- Published by Springer Nature
- p. 396-414
Learning from Others: User Anomaly Detection Using Anomalous Samples from Other Users
- 5 September 2013
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 41 (3) , 871-892
PAKDD’12 best paper: generating balanced classifier-independent training samples from unlabeled data
- 5 September 2013
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 41 (3) , 871-892
PAKDD’12 best paper: generating balanced classifier-independent training samples from unlabeled data