Adversarial Recommendation Attacks

Adversarial Recommendation Attacks is a systematic method designed to manipulate recommendation systems by crafting malicious inputs or perturbations that exploit model vulnerabilities, thereby degrading recommendation accuracy or promoting undesirable items without explicit access to the model's internal parameters.

86

Publications

5.3K

Citations

264

Authors

117

Institutions

Publications per year

2017–2026

53

Variants

Adversarial Attacks On Recommender Systems

Authors

264

  1. BM
    Bamshad Mobasher

    DePaul University, United States

    10 publications · 1.5K citations

    10

    h-index

  2. RB
    Robin Burke

    DePaul University, United States

    9 publications · 1.5K citations

    9

    h-index

  3. RB
    Runa Bhaumik

    University of Illinois Chicago, United States

    6 publications · 1.1K citations

    6

    h-index

  4. CW
    Chad Williams

    DePaul University, United States

    6 publications · 1.1K citations

    6

    h-index

  5. FA
    Felice Antonio Merra

    Polytechnic University of Bari, Italy

    5 publications · 171 citations

    5

    h-index

1–5 of 264

Venues

  1. 4

    h-index

  2. arXiv (Cornell University)

    Repository · 4 publications · 300 citations

    4

    h-index

  3. 3

    h-index

  4. Artificial Intelligence Review

    2 publications · 380 citations

    2

    h-index

  5. 2

    h-index

1–5