Inference attack

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

An Inference Attack is a data mining technique performed by analyzing data in order to illegitimately gain knowledge about a subject or database.[1] A subject's sensitive information can be considered as leaked if an adversary can infer its real value with a high confidence.[2] This is an example of breached information security. An Inference attack occurs when a user is able to infer from trivial information more robust information about a database without directly accessing it.[3] The object of Inference attacks is to piece together information at one security level to determine a fact that should be protected at a higher security level.[4]

While inference attacks were originally discovered as a threat in statistical databases,[5] today they also pose a major privacy threat in the domain of mobile and IoT sensor data. Data from accelerometers, which can be accessed by third-party apps without user permission in many mobile devices,[6] has been used to infer rich information about users based on the recorded motion patterns (e.g., driving behavior, level of intoxication, age, gender, touchscreen inputs, geographic location).[7] Highly sensitive inferences can also be derived, for example, from eye tracking data,[8][9] smart meter data[10][11] and voice recordings (e.g., smart speaker voice commands).[12]


  1. ^ "Inference Attacks on Location Tracks" by John Krumm
  2. ^ "Protecting Individual Information Against Inference Attacks in Data Publishing" by Chen Li, Houtan Shirani-Mehr, and Xiaochun Yang
  3. ^ "Detecting Inference Attacks Using Association Rules" by Sangeetha Raman, 2001
  4. ^ "Database Security Issues: Inference" by Mike Chapple
  5. ^ V. P. Lane (8 November 1985). Security of Computer Based Information Systems. Macmillan International Higher Education. pp. 11–. ISBN 978-1-349-18011-0.
  6. ^ Bai, Xiaolong; Yin, Jie; Wang, Yu-Ping (2017). "Sensor Guardian: prevent privacy inference on Android sensors". EURASIP Journal on Information Security. 2017 (1). doi:10.1186/s13635-017-0061-8. ISSN 2510-523X.
  7. ^ Kröger, Jacob Leon; Raschke, Philip (January 2019). "Privacy implications of accelerometer data: a review of possible inferences". Proceedings of the International Conference on Cryptography, Security and Privacy. ACM, New York. pp. 81–87. doi:10.1145/3309074.3309076.
  8. ^ Liebling, Daniel J.; Preibusch, Sören (2014). "Privacy considerations for a pervasive eye tracking world": 1169–1177. doi:10.1145/2638728.2641688. Cite journal requires |journal= (help)
  9. ^ Kröger, Jacob Leon; Lutz, Otto Hans-Martin; Müller, Florian (2020). "What Does Your Gaze Reveal About You? On the Privacy Implications of Eye Tracking". 576: 226–241. doi:10.1007/978-3-030-42504-3_15. ISSN 1868-4238. Cite journal requires |journal= (help)
  10. ^ Clement, Jana; Ploennigs, Joern; Kabitzsch, Klaus (2014). "Detecting Activities of Daily Living with Smart Meters": 143–160. doi:10.1007/978-3-642-37988-8_10. ISSN 2191-6853. Cite journal requires |journal= (help)
  11. ^ Sankar, Lalitha; Rajagopalan, S.R.; Mohajer, Soheil; Poor, H.V. (2013). "Smart Meter Privacy: A Theoretical Framework". IEEE Transactions on Smart Grid. 4 (2): 837–846. doi:10.1109/TSG.2012.2211046. ISSN 1949-3053.
  12. ^ Kröger, Jacob Leon; Lutz, Otto Hans-Martin; Raschke, Philip (2020). "Privacy Implications of Voice and Speech Analysis – Information Disclosure by Inference". 576: 242–258. doi:10.1007/978-3-030-42504-3_16. ISSN 1868-4238. Cite journal requires |journal= (help)