Network Science Research Lab (NRL)

Research Projects

Censorship Detection

1. Homophone Detection

Using pinyin identify homophones in Mandarin, create a graph-based model of nouns->adjectives and verbs->adverbs to reveal embedded structures and relationships between censored content within the graph.  Since the Chinese language affords the opportunity to construct a large # of homophones we investigate the presence of homophones within censored content.

1. 1. Hiruncharoenvate, C., Lin, Z., & Gilbert, E. (2015, April). Algorithmically bypassing censorship on sina weibo with nondeterministic homophone substitutions. In Ninth International AAAI Conference on Web and Social Media.
   2. Chen, H. C., Vaid, J., & Wu, J. T. (2009). Homophone density and phonological frequency in Chinese word recognition. Language and Cognitive Processes, 24(7-8), 967-982.

Participants:  TBD

2. Network Modeling of Censored Data (parts of speech network, term co-occurrence graphs)

Consensus Formation for neologisms or symbols used to communicate censored messages – maximizing social capital.  We investigate optimization methods such as the simplex model for deciphering which symbols, keywords, homophones or neologisms users select when creating a transformed message to avoid censorship detection.

1. 1. Runck, B. C., Manson, S., Shook, E., Gini, M., & Jordan, N. (2019). Using word embeddings to generate data-driven human agent decision-making from natural language. Geoinformatica, 23(2), 221-242.

Participants:  Raiyan Khan

3. Measuring information entropy for neologisms or symbols using in censored messages

Censored messages often contain neologisms or symbols to bypass censorship detection.  In this project we want to measure how much contextual information is required in for users to understand a messages transformed by using neologisms or symbols.  Information entropy can be used to determine the amount of contextual information required to select the optimal symbol or keyword.

Participants: TBD

4. Data Collection and Analysis Tools

This aim of this project is to develop web scraping tools and, dashboards and searchable user interfaces to collect and analyze online censored content.

Participants:  Jhony Ortiz

Censorship Evasion

1. Linguistic steganography

Investigate the fundamental limits of covert linguistic communication Traditional linguistic stegosystems are based on modification of an existing cover text, e.g., using synonym substitution or paraphrase.

1. 1. Safaka, I., Fragouli, C., & Argyraki, K. (2016). Matryoshka: Hiding secret communication in plain sight. In 6th {USENIX} Workshop on Free and Open Communications on the Internet ({FOCI} 16).
   2. Fang, T., Jaggi, M., & Argyraki, K. (2017). Generating steganographic text with LSTMs. arXiv preprint arXiv:1705.10742.
   3.  Zhang, B., Huang, H., Pan, X., Ji, H., Knight, K., Wen, Z., ... & Yener, B. (2014, June). Be appropriate and funny: Automatic entity morph encoding. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (pp. 706-711).
   4. Ji, H., & Knight, K. (2018, August). Creative language encoding under censorship. In Proceedings of the First Workshop on Natural Language Processing for Internet Freedom (pp. 23-33).

Participants:  Kelly Talavera

2. Internet Measurements of Online Censorship Evasion (Geneva)

This project investigates how network protocols such as TCP/IP can be manipulated to circumvent censors.  Work will focus on identifying strategies and collecting measurements for countries that fail to detect censored content using Geneva.

1. 1. Bock, K., Hughey, G., Merino, L. H., Arya, T., Liscinsky, D., Pogosian, R., & Levin, D. (2020, July). Come as You Are: Helping Unmodified Clients Bypass Censorship with Server-side Evasion. In Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication (pp. 586-598).
   2. Bock, K., Fax, Y., Reese, K., Singh, J., & Levin, D. (2020). Detecting and evading censorship-in-depth: A case study of Iran’s protocol whitelister. In 10th {USENIX} Workshop on Free and Open Communications on the Internet ({FOCI} 20).

Participants:  Irene McGinniss

3. Using covert channels to transmit censored content

A covert channel is a type of attack that creates a capability to transfer information objects between processes that are not supposed to be allowed to communicate by the computer security policy.  The aim of this project is to use timing channels or data hiding to send censored content over email.  An experimental test-bed will need to be established that allows the collection and analysis of cross country email communication.

1. 1. Min, E., Long, J., Liu, Q., Cui, J., & Chen, W. (2018). TR-IDS: Anomaly-based intrusion detection through text-convolutional neural network and random forest. Security and Communication Networks, 2018.

Participants:  Kevin Ortiz

Cybercrime

1. Authorship identification using NLP

This project involves the ongoing issue of Authorship Identification analysis in the realm of Cybercrime identification. The purpose of this research is to analyze and propose a way to identify and analyze the author of text documents in order to more effectively identify cybercriminals within a chosen sample of text documents which includes emails and forum posts

1. 1. Rexha, A., Kröll, M., Ziak, H., & Kern, R. (2018). Authorship identification of documents with high content similarity. Scientometrics, 115(1), 223-237.

Participants:  Dan Kiely

Computational Propaganda

1. Fake News and Bot detection

This project is based on identifying features that can be used to discriminate between human and bot generated content.  Artificial intelligence (AI) remains a crucial aspect for improving our modern lives but it also casts several social and ethical issues.  One issue is of major concern, investigated in this research, is the amount of content users consume that is being generated by a form of AI known as bots (automated software programs). With the rise of social bots and the spread of fake news more research is required to understand how much content generated by bots is being consumed. 

1. 1. Antoun, W., Baly, F., Achour, R., Hussein, A., & Hajj, H. (2020, February). State of the art models for fake news detection tasks. In 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT) (pp. 519-524). IEEE.
   2. Shao, C., Ciampaglia, G. L., Varol, O., Yang, K. C., Flammini, A., & Menczer, F. (2018). The spread of low-credibility content by social bots. Nature communications, 9(1), 1-9.

More information can be found at http://www.mynetcopia.com/nrl/bot-research

Participants:  Megan Ripley, Irene McGinniss, and Chris Wallerstein

2. Interface/Tool Software Development

The aim of this project is to provide users with an intelligent interface or dashboard to decide if a news article contains low credibility content.  Instead of third party fact checking tools we explore human factors that may influence a user’s perception of content quality.

Participants:  Mustafa Alfaouri

Network Security

1. Detecting Rogue Wireless Signals

GPS Spoofing:  Ground based GPS receivers do not contain any method for verifying the source of a GPS signal.  In addition, the transmitted data is not encrypted.  This presents several opportunities for hackers to spoof GPS signals to take control of GPS guided systems such as autonomous vehicles.  This research investigates methods to detect GPS spoofing attacks by identifying unique timing signatures or features that can help distinguish between valid and rogue GPS signals.

1. 1. Zander, S., & Murdoch, S. J. (2008, July). An Improved Clock-skew Measurement Technique for Revealing Hidden Services. In USENIX Security Symposium (pp. 211-226).
   2. Cho, K. T., & Shin, K. G. (2016). Fingerprinting electronic control units for vehicle intrusion detection. In 25th {USENIX} Security Symposium ({USENIX} Security 16) (pp. 911-927).

Participants:  Depion Saha

Wi-Fi Spoofing:  This research study focuses on empirical analysis to elaborate the relationship between received signal strength (RSSI) and distance; investigates methods to detect rogue devices and access points on Wi-Fi networks using network traffic analysis and fingerprint identification methods

1. 3. Sadowski, S., & Spachos, P. (2018). Rssi-based indoor localization with the internet of things. IEEE Access, 6, 30149-30161 highlights Indoor Wi-Fi localization offers better discriminative characteristics in node fingerprinting since it requires low cost to operate.

Participants:  TBD

Projects

Lab Infrastructure

1. Assisting with maintaining lab networking infrastructure and access for lab members.  Development and maintenance of the NetSci Lab Web page

Identify front-end and back-end development tools.  Add new lab members’ information to the site. Update publications and description of lab research projects.  Work with other lab members to integrate applications.  Assist lab members with remote access to computing equipment

Participants:  Ananya Racha

Software Defined Radio and Raspberry Pi Projects

2. Blockchain

The aim of this project to investigate censorship evasion strategies using blockchain.

Participants:  TBD

3. Wireless Mesh Sensor Networking

Design and develop a wireless sensor network for mobility tracking using raspberry Pi’s.  The Pi’s will utilize cameras and ultrasonic sensors to monitor motion and upload images to a database.  Images will contain embedded GPS data for recording image locations.  Should also develop a mobile app so images can be uploaded to a central database.

Participants:  TBD

4. LTE Picocell – low range cellular base station

Implement a cellular base station using software defined radios and Raspberry PI’s In cellular networks, picocells are typically used to extend coverage to indoor areas where outdoor signals do not reach well, or to add network capacity in areas with very dense phone usage, such as train stations or stadiums. 

Participants:  TBD

5. Asterisk soft phone

Asterisk is a free and open source framework for building communications applications.  See https://www.asterisk.org/

Participants:  TBD

6. File tracking

This aim of this project is to develop a Trojan horse application that extracts system information.

For example, you can develop a zip program that will compress a file.  When uncompressed on a user’s computer the MAC address and browser history is saved to a file and emailed to a server

Participants:  TBD

7. Route tracking

Develop an application to record the route a packet takes to reach a specified destination

Participants:  TBD

Past Projects

1. Daniel Chege - MS Cybersecurity (2021)
   1. MS Thesis: “Time of Flight and Fingerprinting Based Methods for Wireless Rogue Device Detection” (https://digitalcommons.montclair.edu/etd/733/)

2. Edmund Genfi -MS Cybersecurity (2021)
   1. MS Thesis: “Detecting Bots Using a Hybrid Approach” (https://digitalcommons.montclair.edu/etd/736/)

3. Wayne Kenney - MS Statistics (2020)
   1. Kenney, W., & Leberknight, C. (2021). User Demographics and Censorship on Sina Weibo. In Proceedings of the 54th Hawaii International Conference on System Sciences (p. 2709).

4. Nivitha Raveendran (MS Computer Science (2019)
   1. Leberknight, C., Raveendran, N. (2018, August). Internet Censorship and Economic Impacts: A case study of Internet outages in India. 24^th AMCIS 2018 Proceedings, 317.

5. Kateryna Kaplun - MS Statistics (2018)
   1. MS Thesis: “Classifying Controversiality in Article Data” (https://digitalcommons.montclair.edu/etd/133/)
   2. Kaplun, K., Leberknight, C., & Feldman, A. (2018, July). Controversy and Sentiment: An Exploratory Study. In Proceedings of the 10th Hellenic Conference on Artificial Intelligence (p. 37). ACM.
   3. Kaplun, K., Leberknight, C., & Feldman, A. (2018, May). A Comparison of Lexicons for Detecting Controversy. In Proceedings of the LREC 2018 Workshop: Natural Language Processing meets Journalism III, Miyazaki (Japan)

6. Eric Joyce – MS in CS (2016) & Matthew Goldeck – BS Computer Science (2019)
   1. Joyce, E., Goldeck, M., Leberknight, C. S., & Feldman, A. (2018, December). Apollo: A System for Tracking Internet Censorship. In Proceedings of the 13th Pre-ICIS Workshop on Information Security and Privacy (Vol. 1).

7. Zhisong Ge - MS Computer Science (2016)
   1. Leberknight, C., Feldman, A. (2019).  Leveraging NLP and Social Network Analytic Techniques to Detect Censored Keywords:  System Design and Experiments 52^nd Hawaii International Conference on System Sciences (HICSS) Maui, Hawaii, USA.

8. Kevin Miller – MS in Computer Science (2016)
   1. Miller, K., & Leberknight, C. (2019, January). cOOKie, a Tool for Developing RF Communication Systems for the Internet of Things. In Proceedings of the 52nd Hawaii International Conference on System Sciences.

9. Raju Vermula - MS in Computer Science (2016)
   1. Poster: PiMesh - implementation of mesh network on multiple raspberry pi’s, Tenth Annual Research Symposium, Montclair State University, April 15, 2016