Corpus ID: 211068813

Adversarial Attacks on Linear Contextual Bandits

@article{Garcelon2020AdversarialAO,
  title={Adversarial Attacks on Linear Contextual Bandits},
  author={Evrard Garcelon and Baptiste Rozi{\`e}re and Laurent Meunier and Jean Tarbouriech and Olivier Teytaud and Alessandro Lazaric and Matteo Pirotta},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.03839}
}
  • Evrard Garcelon, Baptiste Rozière, +4 authors Matteo Pirotta
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • Contextual bandit algorithms are applied in a wide range of domains, from advertising to recommender systems, from clinical trials to education. In many of these domains, malicious agents may have incentives to attack the bandit algorithm to induce it to perform a desired behavior. For instance, an unscrupulous ad publisher may try to increase their own revenue at the expense of the advertisers; a seller may want to increase the exposure of their products, or thwart a competitor's advertising… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.

    Stochastic Linear Bandits Robust to Adversarial Attacks

    VIEW 5 EXCERPTS
    CITES BACKGROUND & RESULTS
    HIGHLY INFLUENCED

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES

    Corruption-tolerant bandit learning

    VIEW 1 EXCERPT

    Adversarial Attacks on Stochastic Bandits

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Data Poisoning Attacks in Contextual Bandits

    VIEW 2 EXCERPTS

    Data Poisoning Attacks on Stochastic Bandits

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Adversarial Bandits with Knapsacks