ABSTRACT
Protecting the user's personality privacy can effectively interfere with or deceive the attacker's personality analysis, avoid the attacker's use of personality vulnerability, and reduce the success rate of social engineering attacks. However, the current research on personality privacy protection is at a blank stage. To solve this problem, we propose a personality privacy protection method based on adversarial text generation. This paper mainly uses gradient-based adversarial method and cosine similarity to generation adversarial text. We formed a set of replacement words to test the impact of the number of replacement words on the performance of the model. Experiments show that the method proposed in this paper has achieved good effects on model attacks (reducing the performance of the model), and can well complete the task of protecting personality privacy.
- Mitnick K D, Simon W L. The art of deception: Controlling the human element of security. John Wiley & Sons, 2011.Google Scholar
- Stewart Jr J H. Social engineering deception susceptibility: Modification of personality traits susceptible to social engineering manipulation to acquire information through attack and exploitation. Colorado Technical University, 2015.Google Scholar
- Irani D, Balduzzi M, Balzarotti D, Reverse Social Engineering Attacks in Online Social Networks. Springer Berlin Heidelberg, 2011:55-74.Martin A. Fischler and Robert C. Bolles. 1981. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24, 6 (June 1981), 381–395. https://doi.org/10.1145/358669.358692Google ScholarDigital Library
- Krombholz K, Hobel H, Huber M, Advanced social engineering attacks. Journal of Information Security and applications, 2015, 22: 113-122.Google Scholar
- Monsted, Bjarke, Mollgaard A, Mathiesen J. Phone-based Metric as a Predictor for Basic Personality Traits[J]. Journal of Research in Personality, 2016, 74.Google Scholar
- Abraham S, Chengalur-Smith I S. An overview of social engineering malware: Trends, tactics, and implications. Technology in Society, 2010, 32(3): 183-196.Google ScholarCross Ref
- Bezuidenhout M, Mouton F, Venter H S. Social engineering attack detection model: Seadm.Information Security for South Africa , 2010. IEEE, 2010: 1-8.Google ScholarCross Ref
- Hsin-Chang Yang, Chung-Hong Lee, and Chia-Yi Yeh. 2020. Mining Personality Traits from Social Text Messages. In Proceedings of the 7th Multidisciplinary in International Social Networks Conference and The 3rd International Conference on Economics, Management and Technology (MISNC2020&IEMT2020). Association for Computing Machinery, New York, NY, USA, Article 17, 1–5. DOI:https://doi.org/10.1145/3429395.3429412Google ScholarDigital Library
- El-Demerdash K, El-Khoribi R A, Shoman M A I, Deep learning based fusion strategies for personality prediction[J]. Egyptian Informatics Journal, 2021.Google ScholarCross Ref
- Rohit G V, Bharadwaj K R, Hemanth R, Machine intelligence based personality prediction using social profile data[C]//2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT). IEEE, 2020: 1003-1008.Google Scholar
- Wang S, Cui L, Liu L, Personality Traits Prediction Based on Users’ Digital Footprints in Social Networks via Attention RNN[C]//2020 IEEE International Conference on Services Computing (SCC). IEEE, 2020: 54-56.Google Scholar
- Leonardi S, Monti D, Rizzo G, Multilingual Transformer-Based Personality Traits Estimation[J]. Information, 2020, 11(4): 179.Google ScholarCross Ref
- Almlund M, Duckworth A, Heckman J J, Personality Psychology and Economics. Iza Discussion Papers, 2011, 51(3):1–181.Google Scholar
- McCrae R R, Weiss A. Observer ratings of personality. Handbook of research methods in personality psychology, 2007: 259-272.Google Scholar
- N. Thakur and C. Y. Han, “An Ambient Intelligence-Based Human Behavior Monitoring Framework for Ubiquitous Environments,” Journal of Information, vol. 12, no. 2, p. 81, Feb. 2021.Google ScholarCross Ref
- Park G, Schwartz H A, Eichstaedt J C, Automatic personality assessment through social media language. Journal of personality and social psychology, 2015, 108(6): 934.Google Scholar
- Tadesse M M , Lin H , Xu B , Personality Predictions Based on User Behaviour on the Facebook Social Media Platform[J]. IEEE Access, 2018:1-1.Google Scholar
- Bleidorn W , Hopwood C J . Using Machine Learning to Advance Personality Assessment and Theory[J]. Personality and Social Psychology Review, 2018:108886831877299.Google Scholar
- Arnoux P H , Xu A , Boyette N , 25 Tweets to Know You: A New Model to Predict Personality with Social Media[J]. 2017.Google Scholar
- G. Chittaranjan, J. Blom, and D. Gatica-Perez. Who's who with big-five: Analyzing and classifying personality traits with smartphones. In IEEE Annual International Symposium on Wearable Computers, 2011, pp. 29–36.Google ScholarDigital Library
- J. Staiano, F. Pianesi, B. Lepri, N. Sebe, Friends don't lie:Inferring personality traits from social network structure. In Proceedings of the ACM International Conference on Ubiquitous Computing, 2012, pp. 321–330.Google Scholar
- M. Pattinson, C. JeRRAM, K. Parsons, A. McCormac, M. Butavicius. Why do some people manage phishing e-mails better than others? Information Management & Computer Security, 2012.Google ScholarCross Ref
- Darwish, A. E. Zarka, F. Aloul. Towards understanding phishing victims' profile. International Conference on Computer Systems and Industrial Informatics, 2012.Google ScholarCross Ref
- Halevi T, Memon N, Nov O. Spear-Phishing in the Wild: A Real-World Study of Personality, Phishing Self-Efficacy and Vulnerability to Spear-Phishing Attacks. Social Science Electronic Publishing, 2015.Google Scholar
- Parrish J L, Bailey J L, Courtney J F. A Personality Based Model for Determining Susceptibility to Phishing Attacks. 2009.Google Scholar
- Devlin J, Chang M W, Lee K, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding[J]. 2018.Google Scholar
- Wang X, Yang Y, Deng Y, Fast Gradient Projection Method for Text Adversary Generation and Adversarial Training[J]. 2020.Google Scholar
- Markovikj, Dejan and Gievska, Sonja and Kosinski, Michal and Stillwell, David J. Mining facebook data for predictive personality modeling. In Seventh International AAAI Conference on Weblogs and Social Media 2013.Google Scholar
Recommendations
Adversarial Machine Learning for Text
IWSPA '20: Proceedings of the Sixth International Workshop on Security and Privacy AnalyticsIn this tutorial, we investigate the history, evolution and latest research topics in the area of adversarial machine learning for text data. Both classical attacks on spam filters and more recent attacks on deep learning models for text classification ...
Frequency-based Adversarial Privacy Protection Strategy Against Face Recognition Neural NetworksFrequency-based Adversarial Privacy Protection Strategy
ICMLCA '23: Proceedings of the 2023 4th International Conference on Machine Learning and Computer ApplicationOver the past few years, countless videos and images have been uploaded to social media platforms every day, which presents a challenge in how to protect the private data of large numbers of users. At the same time, face recognition algorithms have ...
Comments