2024 · 16 citations · 29 references
ComputingComputer EngineeringComputer ScienceComputer SecurityMachine LearningSecurity ArchitectureAdversary TechniquesDeep LearningEnsemble LearningEnsemble MethodsOverfittingScalable Machine LearningAdversarial Attack DetectionAdversarial LossAdversarial RobustnessNeural Ranking ModelsRanking Models
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 or sentence level, to target documents. However, limiting perturbations to a single level of granularity may reduce the flexibility of adversarial examples, thereby diminishing the potential threat of the attack. Therefore, we focus on generating high-quality adversarial examples by incorporating multi-granular perturbations. Achieving this objective involves tackling a combinatorial explosion problem, which requires identifying an optimal combination of perturbations across all possible levels of granularity, positions, and textual pieces. To address this challenge, we transform the multi-granular adversarial attack into a sequential decision-making process, where perturbations in the next attack step build on the perturbed document in the current attack step. Since the attack process can only access the final state without direct intermediate signals, we use reinforcement learning to perform multi-granular attacks. During the reinforcement learning process, two agents work cooperatively to identify multi-granular vulnerabilities as attack targets and organize perturbation candidates into a final perturbation sequence. Experimental results show that our attack method surpasses prevailing baselines in both attack effectiveness and imperceptibility.
29
A vector space model for automatic indexing
Gerard Salton, Anita M.-Y. Wong, Chul‐Su Yang · Communications of the ACM · 1975 · 7.4K citations · Full text
A language modeling approach to information retrieval
Jay Ponte, W. Bruce Croft · 1998 · 1.7K citations
HotFlip: White-Box Adversarial Examples for Text Classification
Javid Ebrahimi, Anyi Rao, Daniel Lowd et al. · 2018 · 900 citations · Full text