bibliography.bib

@misc{boucher2021bad,
  title         = {Bad Characters: Imperceptible NLP Attacks},
  author        = {Nicholas Boucher and Ilia Shumailov and Ross Anderson and Nicolas Papernot},
  year          = {2021},
  eprint        = {2106.09898},
  archiveprefix = {arXiv},
  primaryclass  = {cs.CL}
}

@article{https://doi.org/10.1002/aris.1440370103,
  author  = {Chowdhury, Gobinda G.},
  title   = {Natural language processing},
  journal = {Annual Review of Information Science and Technology},
  volume  = {37},
  number  = {1},
  pages   = {51-89},
  doi     = {https://doi.org/10.1002/aris.1440370103},
  url     = {https://asistdl.onlinelibrary.wiley.com/doi/abs/10.1002/aris.1440370103},
  eprint  = {https://asistdl.onlinelibrary.wiley.com/doi/pdf/10.1002/aris.1440370103},
  year    = {2003}
}

@article{doi:10.1126/science.aaa8685,
  author   = {Julia Hirschberg  and Christopher D. Manning },
  title    = {Advances in natural language processing},
  journal  = {Science},
  volume   = {349},
  number   = {6245},
  pages    = {261-266},
  year     = {2015},
  doi      = {10.1126/science.aaa8685},
  url      = {https://www.science.org/doi/abs/10.1126/science.aaa8685},
  eprint   = {https://www.science.org/doi/pdf/10.1126/science.aaa8685},
  abstract = {Natural language processing employs computational techniques for the purpose of learning, understanding, and producing human language content. Early computational approaches to language research focused on automating the analysis of the linguistic structure of language and developing basic technologies such as machine translation, speech recognition, and speech synthesis. Today’s researchers refine and make use of such tools in real-world applications, creating spoken dialogue systems and speech-to-speech translation engines, mining social media for information about health or finance, and identifying sentiment and emotion toward products and services. We describe successes and challenges in this rapidly advancing area.}
}

@misc{moore1965cramming,
  title     = {Cramming more components onto integrated circuits},
  author    = {Moore, Gordon E and others},
  year      = {1965},
  publisher = {McGraw-Hill New York}
}

@article{jordan2015machine,
  title     = {Machine learning: Trends, perspectives, and prospects},
  author    = {Jordan, Michael I and Mitchell, Tom M},
  journal   = {Science},
  volume    = {349},
  number    = {6245},
  pages     = {255--260},
  year      = {2015},
  publisher = {American Association for the Advancement of Science}
}

@article{gopalakrishnan2018deep,
  title     = {Deep learning in data-driven pavement image analysis and automated distress detection: A review},
  author    = {Gopalakrishnan, Kasthurirangan},
  journal   = {Data},
  volume    = {3},
  number    = {3},
  pages     = {28},
  year      = {2018},
  publisher = {Multidisciplinary Digital Publishing Institute}
}

@misc{https://doi.org/10.48550/arxiv.1911.07399,
  doi       = {10.48550/ARXIV.1911.07399},
  url       = {https://arxiv.org/abs/1911.07399},
  author    = {Huang, Xijie and Alzantot, Moustafa and Srivastava, Mani},
  keywords  = {Cryptography and Security (cs.CR), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title     = {NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations},
  publisher = {arXiv},
  year      = {2019},
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@article{adversexamples,
  author = {Aleksander Mądry and Ludwig Schmidt },
  title  = {A Brief Introduction to Adversarial Examples},
  year   = {2018},
  doi    = {10.1126/science.aaa8685},
  url    = {https://gradientscience.org/intro_adversarial/}
}

@inproceedings{spamfilter,
  author    = {Kuchipudi, Bhargav and Nannapaneni, Ravi Teja and Liao, Qi},
  title     = {Adversarial Machine Learning for Spam Filters},
  year      = {2020},
  isbn      = {9781450388337},
  publisher = {Association for Computing Machinery},
  address   = {New York, NY, USA},
  url       = {https://doi.org/10.1145/3407023.3407079},
  doi       = {10.1145/3407023.3407079},
  abstract  = {Email spam filters based on machine learning techniques are widely deployed in today's organizations. As our society relies more on artificial intelligence (AI), the security of AI, especially the machine learning algorithms, becomes increasingly important and remains largely untested. Adversarial machine learning, on the other hand, attempts to defeat machine learning models through malicious input. In this paper, we experiment how adversarial scenario may impact the security of machine learning based mechanisms such as email spam filters. Using natural language processing (NLP) and Baysian model as an example, we developed and tested three invasive techniques, i.e., synonym replacement, ham word injection and spam word spacing. Our adversarial examples and results suggest that these techniques are effective in fooling the machine learning models. The study calls for more research on understanding and safeguarding machine learning based security mechanisms in the presence of adversaries.},
  booktitle = {Proceedings of the 15th International Conference on Availability, Reliability and Security},
  articleno = {38},
  numpages  = {6},
  keywords  = {adversarial machine learning, network security, spam detection, artificial intelligence},
  location  = {Virtual Event, Ireland},
  series    = {ARES '20}
}

@inproceedings{neural,
	doi = {10.18653/v1/2020.acl-main.540},
  
	url = {https://doi.org/10.18653%2Fv1%2F2020.acl-main.540},
  
	year = 2020,
	publisher = {Association for Computational Linguistics},
  
	author = {Yuan Zang and Fanchao Qi and Chenghao Yang and Zhiyuan Liu and Meng Zhang and Qun Liu and Maosong Sun},
  
	title = {Word-level Textual Adversarial Attacking as Combinatorial Optimization},
  
	booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics}
}

@inproceedings{pruthi2019,
    title = "Combating Adversarial Misspellings with Robust Word Recognition",
    author = "Pruthi, Danish  and
      Dhingra, Bhuwan  and
      Lipton, Zachary C.",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/P19-1561",
    doi = "10.18653/v1/P19-1561",
    pages = "5582--5591",
    abstract = "To combat adversarial spelling mistakes, we propose placing a word recognition model in front of the downstream classifier. Our word recognition models build upon the RNN semi-character architecture, introducing several new backoff strategies for handling rare and unseen words. Trained to recognize words corrupted by random adds, drops, swaps, and keyboard mistakes, our method achieves 32{\%} relative (and 3.3{\%} absolute) error reduction over the vanilla semi-character model. Notably, our pipeline confers robustness on the downstream classifier, outperforming both adversarial training and off-the-shelf spell checkers. Against a BERT model fine-tuned for sentiment analysis, a single adversarially-chosen character attack lowers accuracy from 90.3{\%} to 45.8{\%}. Our defense restores accuracy to 75{\%}. Surprisingly, better word recognition does not always entail greater robustness. Our analysis reveals that robustness also depends upon a quantity that we denote the sensitivity.",
}

@INPROCEEDINGS{twitternlp,  author={Kandasamy, Kamalanathan and Koroth, Preethi},  booktitle={2014 IEEE Students' Conference on Electrical, Electronics and Computer Science},   title={An integrated approach to spam classification on Twitter using URL analysis, natural language processing and machine learning techniques},   year={2014},  volume={},  number={},  pages={1-5},  doi={10.1109/SCEECS.2014.6804508}}

@INPROCEEDINGS{spam,  author={Garg, Pranjul and Girdhar, Nancy},  booktitle={2021 11th International Conference on Cloud Computing, Data Science \& Engineering (Confluence)},   title={A Systematic Review on Spam Filtering Techniques based on Natural Language Processing Framework},   year={2021},  volume={},  number={},  pages={30-35},  doi={10.1109/Confluence51648.2021.9377042}}

@inproceedings{hate,
    title = "A Survey on Hate Speech Detection using Natural Language Processing",
    author = "Schmidt, Anna  and
      Wiegand, Michael",
    booktitle = "Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W17-1101",
    doi = "10.18653/v1/W17-1101",
    pages = "1--10",
    abstract = "This paper presents a survey on hate speech detection. Given the steadily growing body of social media content, the amount of online hate speech is also increasing. Due to the massive scale of the web, methods that automatically detect hate speech are required. Our survey describes key areas that have been explored to automatically recognize these types of utterances using natural language processing. We also discuss limits of those approaches.",
}

@inproceedings{falsereview,
	address = {Singapore},
	title = {Deep {Sentiments} {Extraction} for {Consumer} {Products} {Using} {NLP}-{Based} {Technique}},
	isbn = {978-981-13-3393-4},
	abstract = {The growth in the field of e-commerce and product availability over the Internet is the higher availability of the consumable items is making the customers seek for higher quality and comparative price points. The primary reason for this ambiguity is the lack of in hand experience for the customers before the purchase. The customers mostly tend to rely on the feedbacks of the other buyers. The feedbacks on the products are often made in thousands in numbers, and it is difficult for the potential buyers to decide by looking into these feedbacks or reviews. Thus the demand of the modern research is to automate the process for extracting the true feedback matching their needs based on usage or price or location constraints. The feedback or the review system can be easily manipulated by the incorrect feedbacks. Hence it is important to reduce the influence of those feedbacks during extracting the overall sentiment of any product. Also, yet another challenge is that most of the feedbacks are not in formal English, thus making it difficult to extract the accurate feedback. This work proposes a novel-automated frame for extracting the deep sentiments from the reviews or the feedbacks on e-commerce websites. Another major outcome of this work is to detect the false reviews and making the sentiment true for any decision making. The research work generates a trustable sentiment extraction process to justify the need of true feedbacks for customer decision making.},
	booktitle = {Soft {Computing} and {Signal} {Processing}},
	publisher = {Springer Singapore},
	author = {Trupthi, Mandhula and Pabboju, Suresh and Gugulotu, Narsimha},
	editor = {Wang, Jiacun and Reddy, G. Ram Mohana and Prasad, V. Kamakshi and Reddy, V. Sivakumar},
	year = {2019},
	pages = {191--201},
}

@INPROCEEDINGS{sentimentality,  author={Yi, J. and Nasukawa, T. and Bunescu, R. and Niblack, W.},  booktitle={Third IEEE International Conference on Data Mining},   title={Sentiment analyzer: extracting sentiments about a given topic using natural language processing techniques},   year={2003},  volume={},  number={},  pages={427-434},  doi={10.1109/ICDM.2003.1250949}}

@inproceedings{hatespeech,
author = {Gr\"{o}ndahl, Tommi and Pajola, Luca and Juuti, Mika and Conti, Mauro and Asokan, N.},
title = {All You Need is "Love": Evading Hate Speech Detection},
year = {2018},
isbn = {9781450360043},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3270101.3270103},
doi = {10.1145/3270101.3270103},
booktitle = {Proceedings of the 11th ACM Workshop on Artificial Intelligence and Security},
pages = {2-12},
numpages = {11},
keywords = {adversarial training, evasion attacks, supervised learning, adversarial examples, deep learning, logistic regression, classification, hate speech, neural networks},
location = {Toronto, Canada},
series = {AISec '18}
}

@article{tesseractocr,
  title={Optical character recognition by open source OCR tool tesseract: A case study},
  author={Patel, Chirag and Patel, Atul and Patel, Dharmendra},
  journal={International Journal of Computer Applications},
  volume={55},
  number={10},
  pages={50--56},
  year={2012},
  publisher={Electronic Publication: Digital Object Identifiers (DOIs)}
}

@misc{dnedefense,
  doi = {10.48550/ARXIV.2006.11627},
  
  url = {https://arxiv.org/abs/2006.11627},
  
  author = {Zhou, Yi and Zheng, Xiaoqing and Hsieh, Cho-Jui and Chang, Kai-wei and Huang, Xuanjing},
  
  keywords = {Computation and Language (cs.CL), Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
  
  title = {Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble},
  
  publisher = {arXiv},
  
  year = {2020},
  
  copyright = {arXiv.org perpetual, non-exclusive license}
}

@article{phishing,
  author={Khonji, Mahmoud and Iraqi, Youssef and Jones, Andrew},
  journal={IEEE Communications Surveys \& Tutorials}, 
  title={Phishing Detection: A Literature Survey}, 
  year={2013},
  volume={15},
  number={4},
  pages={2091-2121},
  doi={10.1109/SURV.2013.032213.00009}}

@inproceedings{moderation,
author = {Steiger, Miriah and Bharucha, Timir J and Venkatagiri, Sukrit and Riedl, Martin J. and Lease, Matthew},
title = {The Psychological Well-Being of Content Moderators: The Emotional Labor of Commercial Moderation and Avenues for Improving Support},
year = {2021},
isbn = {9781450380966},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3411764.3445092},
doi = {10.1145/3411764.3445092},
booktitle = {Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems},
articleno = {341},
numpages = {14},
keywords = {wellness, content moderation, social justice, human computation},
location = {Yokohama, Japan},
series = {CHI '21}
}

@article{hoxhunt,
  title={Tekstiviestit s{\"a}hk{\"o}postiperustaisen tietojenkalastelun tehokeinona},
  author={Keski-Pukkila, Pontus},
  year={2019}
}

@article{stats-phishing,
title = {Assessing the severity of phishing attacks: A hybrid data mining approach},
journal = {Decision Support Systems},
volume = {50},
number = {4},
pages = {662-672},
year = {2011},
note = {Enterprise Risk and Security Management: Data, Text and Web Mining},
issn = {0167-9236},
doi = {https://doi.org/10.1016/j.dss.2010.08.020},
url = {https://www.sciencedirect.com/science/article/pii/S0167923610001442},
author = {Xi Chen and Indranil Bose and Alvin Chung Man Leung and Chenhui Guo},
keywords = {Financial loss, Phishing, Risk, Supervised classification, Text phrase extraction, Variable importance}
}

@article{indirect,
  title={Indirect financial loss of phishing to global market},
  author={Leung, Alvin and Bose, Indranil},
  year={2008}
}

@article{hatespeech-stats,
author = {Fortuna, Paula and Nunes, S\'{e}rgio},
title = {A Survey on Automatic Detection of Hate Speech in Text},
year = {2018},
issue_date = {July 2019},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {51},
number = {4},
issn = {0360-0300},
url = {https://doi.org/10.1145/3232676},
doi = {10.1145/3232676},
journal = {ACM Comput. Surv.},
month = {jul},
articleno = {85},
numpages = {30},
keywords = {literature review, Hate speech, text mining, natural language processing, opinion mining}
}

@article{fakereview-stats,
title = {A framework for fake review detection in online consumer electronics retailers},
journal = {Information Processing \& Management},
volume = {56},
number = {4},
pages = {1234-1244},
year = {2019},
issn = {0306-4573},
doi = {https://doi.org/10.1016/j.ipm.2019.03.002},
url = {https://www.sciencedirect.com/science/article/pii/S030645731730657X},
author = {Rodrigo Barbado and Oscar Araque and Carlos A. Iglesias},
keywords = {Fake Review, Sentiment Analysis, Machine Learning, Data Analysis, Web Analytics},
}