Can pre-trained Transformers be used in detecting complex sensitive sentences? - A Monsanto case study

Timmer, Roelien C.; Liebowitz, David; Nepal, Surya; Kanhere, Salil S.

doi:10.1109/tpsisa52974.2021.00010

Cited by 4 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vendor Identification; A Text Similarity task: Text-similarity techniques are not new to the researchers in the field of AA (Sapkota et al, 2013;Castro Castro et al, 2015;Rexha et al, 2018;Boenninghoff et al, 2019). However, with the recent success of transformers (Reimers and Gurevych, 2019a;Yang et al, 2019b;Jiang et al, 2022), researchers are now investigating the application of semantically meaningful representations for paraphrasing detection (Timmer et al, 2021;Olney, 2021;Ko and Choi, 2020), text summarization (Miller, 2019;Cai et al, 2022), semantic pars-ing (Ge et al, 2019;Ferraro and Suominen, 2020), question answering (Yang et al, 2019a;Vold and Conrad, 2021;Louis and Spanakis, 2021), and AA (Fabien et al, 2020;Li et al, 2020;Custódio and Paraboni, 2021;Uchendu et al, 2020b).…”

Section: Related Researchmentioning

confidence: 99%

VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets

Saxena¹,

Rethmeier²,

Dijck³

et al. 2023

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

The anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between markets. Consequently, illegal markets and their connections are challenging to uncover on the Darknet. To identify relationships between illegal markets and their vendors, we propose Ven-dorLink, an NLP-based approach that examines writing patterns to verify, identify, and link unique vendor accounts across text advertisements (ads) on seven public Darknet markets. In contrast to existing literature, VendorLink utilizes the strength of supervised pre-training to perform closed-set vendor verification, openset vendor identification, and low-resource market adaption tasks. Through VendorLink, we uncover (i) 15 migrants and 71 potential aliases in the Alphabay-Dreams-Silk dataset, (ii) 17 migrants and 3 potential aliases in the Valhalla-Berlusconi dataset, and (iii) 75 migrants and 10 potential aliases in the Traderoute-Agora dataset. Altogether, our approach can help Law Enforcement Agencies (LEA) make more informed decisions by verifying and identifying migrating vendors and their potential aliases on existing and Low-Resource (LR) emerging Darknet markets. 1

show abstract

Section: Related Researchmentioning

confidence: 99%

VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets

Saxena¹,

Rethmeier²,

Dijck³

et al. 2023

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

show abstract

“…Recent use of fine-tuning on pre-trained Transformer language models has proven effective on a range of NLP tasks, and we have subsequently tested this idea on sensitive information detection. In [45], we experiment with the finetuned Bidirectional Encoder Representations from Transformers (BERT) [46]. This method is graphically represented in Figure 7.…”

Section: A Creating Documentsmentioning

confidence: 99%

Deception for Cyber Defence: Challenges and Opportunities

Liebowitz

Nepal

Moore

et al. 2021

2021 Third IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA)

Self Cite

View full text Add to dashboard Cite

Deception is rapidly growing as an important tool for cyber defence, complementing existing perimeter security measures to rapidly detect breaches and data theft. One of the factors limiting the use of deception has been the cost of generating realistic artefacts by hand. Recent advances in Machine Learning have, however, created opportunities for scalable, automated generation of realistic deceptions. This vision paper describes the opportunities and challenges involved in developing models to mimic many common elements of the IT stack for deception effects.

show abstract

Sensitive Content Detection in Social Networks Using Deep Learning Models and Explainability Techniques

Perikos

2024

2024 IEEE/ACIS 9th International Conference on Big Data, Cloud Computing, and Data Science (BCD)

View full text Add to dashboard Cite

Can pre-trained Transformers be used in detecting complex sensitive sentences? - A Monsanto case study

Cited by 4 publications

References 13 publications

VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets

VendorLink: An NLP approach for Identifying & Linking Vendor Migrants & Potential Aliases on Darknet Markets

Deception for Cyber Defence: Challenges and Opportunities

Sensitive Content Detection in Social Networks Using Deep Learning Models and Explainability Techniques

Contact Info

Product

Resources

About