eDarkFind: Unsupervised Multi-view Learning for Sybil Account Detection

Ramnath, Kumar,; Yadav, Shweta; Daniulaityte, Raminta; Lamy, François; Thirunarayan, Krishnaprasad; Lokala, Usha; Sheth, Amit P.

doi:10.1145/3366423.3380263

Cited by 17 publications

(26 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Crawling cryptomarkets poses a significant challenge to apply data science and machine learning to study the opioid epidemic due to the restricted crawling process (Kumar et al 2020;. To identify the best strategies to reduce opioid misuse, a better understanding of cryptomarket drug sales that impact consumption and how it reflects social media discussions is needed (Kamdar et al 2019).…”

Section: Discussionmentioning

confidence: 99%

“…Concerning Dark web data, three cryptomarkets, Dream market, Tochka, and WallStreet Market, were periodically crawled in between March 2018 and January 2019. Over 70,000 opioid-related listings were collected using the dedicated crawler (Kumar et al 2020;. Raw HTML files collected were parsed and processed using a Named Entity Recognition (NER) to further extract substance names, product weight, price of the product, shipment information, availability, and administration route as shown in Table 1.…”

Section: Data Collectionmentioning

confidence: 99%

See 1 more Smart Citation

eDarkTrends: Harnessing Social Media Trends in Substance use disorders for Opioid Listings on Cryptomarket

Lokala¹,

Lamy²,

Dastidar³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Opioid and substance misuse is rampant in the United States today, with the phenomenon known as the "opioid crisis". The relationship between substance use and mental health has been extensively studied, with one possible relationship being; substance misuse causes poor mental health. However, the lack of evidence on the relationship has resulted in opioids being largely inaccessible through legal means. This study analyzes the substance misuse posts on social media with the opioids being sold through cryptomarket listings. We use the Drug Abuse Ontology, state-of-the-art deep learning, and BERT-based models to generate sentiment and emotion for the social media posts to understand users' perception on social media by investigating questions such as: which synthetic opioids people are optimistic, neutral, or negative about? or what kind of drugs induced fear and sorrow? or what kind of drugs people love or thankful about? or which drug people think negatively about? or which opioids cause little to no sentimental reaction. We also perform topic analysis associated with the generated sentiments and emotions to understand which topics correlate with people's responses to various drugs. Our findings can help shape policy to help isolate opioid use cases where timely intervention may be required to prevent adverse consequences, prevent overdose-related deaths, and worsen the epidemic.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Data Collectionmentioning

confidence: 99%

eDarkTrends: Harnessing Social Media Trends in Substance use disorders for Opioid Listings on Cryptomarket

Lokala¹,

Lamy²,

Dastidar³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…content, photography style, user profile and drug information). Similarly, Kumar et al (2020) proposed a multiview unsupervised approach which incorporated features of text content, drug substances, and locations to generate vendor embeddings. We note that while such efforts (Zhang et al, 2019;Kumar et al, 2020) are related to our work, there are key distinctions.…”

Section: Related Workmentioning

confidence: 99%

“…The research conducted in this study was deemed to be exempt research by the Ohio State University's Office of Responsible Research Practices, since the forum data is classified as 'publicly available'. Darknet forum data is readily available publicly across multiple markets (Branwen et al, 2015;Munksgaard and Demant, 2016) and we follow standard practices for the darkweb (Kumar et al, 2020) limiting our analysis to publicly available information only. The data was originally collected to study the prevalence of illicit drug trade and the politics surrounding such trades.…”

Section: A Ethics Statementmentioning

confidence: 99%

SYSML: StYlometry with Structure and Multitask Learning: Implications for Darknet Forum Migrant Analysis

Maneriker¹,

He²,

Parthasarathy³

2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Darknet market forums are frequently used to exchange illegal goods and services between parties who use encryption to conceal their identities. The Tor network is used to host these markets, which guarantees additional anonymization from IP and location tracking, making it challenging to link across malicious users using multiple accounts (sybils). Additionally, users migrate to new forums when one is closed further increasing the difficulty of linking users across multiple forums. We develop a novel stylometry-based multitask learning approach for natural language and model interactions using graph embeddings to construct low-dimensional representations of short episodes of user activity for authorship attribution. We provide a comprehensive evaluation of our methods across four different darknet forums demonstrating its efficacy over the state-of-the-art, with a lift of up to 2.5X on Mean Retrieval Rank and 2X on Recall@10.

show abstract

“…In this work, we propose a multi-view learning framework [20] that jointly models both the content and the contextualinformation specific for the tasks. It begins by processing contextual information using several NLU views such as emotions, personality, sentiments, and use of figurative language (FL).…”

Section: Introductionmentioning

confidence: 99%