Multi-granular Adversarial Attacks against Black-box Neural Ranking Models

arXiv:2404.01574v1 Announce Type: cross
Abstract: Adversarial ranking attacks have gained increasing attention due to their success in probing vulnerabilities, and, hence, enhancing the robustness, of neural ranking models. Conventional attack methods employ perturbations at a single granularity, e.g., word-level or sentence-level, to a target document. However, limiting perturbations to a single level of granularity may reduce the flexibility of creating adversarial examples, thereby diminishing the potential threat of the attack. Therefore, we focus on generating high-quality adversarial examples by incorporating …

abstract adversarial adversarial attacks arxiv attack methods attacks attention box cs.cr cs.ir cs.lg document however ranking robustness success type vulnerabilities word