Inference Threats

Inference Threat refers to a privacy threat where an adversary deduces sensitive information from indirect, seemingly non-sensitive data through statistical, logical, or machine learning techniques, thereby compromising confidentiality despite the absence of direct data access.

17

Publications

1.5K

Citations

46

Authors

32

Institutions

Publications per year

2017–2026

10

Authors

46

  1. MF
    Matt Fredrikson

    Carnegie Mellon University, United States

    3 publications · 935 citations

    3

    h-index

  2. SJ
    Somesh Jha

    University of Wisconsin–Madison, United States

    3 publications · 935 citations

    3

    h-index

  3. SY
    Samuel Yeom

    Carnegie Mellon University, United States

    3 publications · 935 citations

    3

    h-index

  4. IG
    Irene Giacomelli

    University of Florence, Italy

    2 publications · 915 citations

    2

    h-index

  5. MC
    Melissa Chase

    Microsoft (United States), United States

    1 publications · 63 citations

    1

    h-index

1–5 of 46

Venues

  1. arXiv (Cornell University)

    Repository · 3 publications · 129 citations

    3

    h-index

  2. 2022 IEEE Symposium on Security and Privacy (SP)

    Conference · 1 publications · 63 citations

    1

    h-index

  3. Information Sciences

    1 publications · 19 citations

    1

    h-index

  4. 1

    h-index

  5. International Journal of Intelligent Systems

    1 publications · 26 citations

    1

    h-index

1–5