Lune

ACL Findings2023

Towards Imperceptible Document Manipulations against Neural Ranking Models

Xuanang Chen, Ben He, Zheng Ye, Le Sun, Yingfei Sun

Abstract

Adversarial attacks have gained traction in order to identify vulnerabilities in neural ranking models (NRMs), but current attack methods often introduce noticeable errors. Moreover, current methods rely heavily on using a well-imitated surrogate NRM to guarantee the attack effect, making them difficult to use in practice. This paper proposes a framework called Imperceptible DocumEnt Manipulation (IDEM) to produce adversarial documents that are less noticeable to both algorithms and humans. IDEM instructs a well-established generative language model like BART to generate error-free connection sentences, and employs a separate position-wise merging strategy to balance between relevance and coherence of the perturbed text. Evaluation results on the MS MARCO benchmark demonstrate that IDEM outperforms strong baselines while preserving fluency and correctness of the target documents. Furthermore, the separation of adversarial text generation from the surrogate NRM makes IDEM more robust and less affected by the quality of the surrogate NRM.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

7 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Stop Hardening Everything: A Training-Free Neuron-Level Defense for Neural Ranking Models cites Document Ranking with a Pretrained Sequence-to-Sequence Model
  • Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrieval cites Dense Passage Retrieval for Open-Domain Question Answering
  • Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrieval cites Multi-granular Adversarial Attacks against Black-box Neural Ranking Models
  • Document Ranking with a Pretrained Sequence-to-Sequence Model cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
  • Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-Box Neural Ranking Models cites Multi-granular Adversarial Attacks against Black-box Neural Ranking Models
  • Dense Passage Retrieval for Open-Domain Question Answering cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
  • Dense Passage Retrieval for Open-Domain Question Answering cites ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
  • Multi-granular Adversarial Attacks against Black-box Neural Ranking Models cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
  • Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systems cites Dense Passage Retrieval for Open-Domain Question Answering
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers7

  1. Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM SystemsHongyan Chang, Ergute Bao, Xinjian Luo, Ting YuUSENIX Security 2026 · 24 citations
  2. Multi-granular Adversarial Attacks against Black-box Neural Ranking ModelsYu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke et al.SIGIR 2024 · 17 citations
  3. Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-Box Neural Ranking ModelsYu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke et al.AAAI 2025 · 11 citations
  4. Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense RetrievalYongkang Li, Panagiotis Eustratiadis, Simon Lupart, Evangelos KanoulasSIGIR 2025 · 3 citations
  5. Stop Hardening Everything: A Training-Free Neuron-Level Defense for Neural Ranking ModelsYu-An Liu, Ruqing Zhang, Hongru Song, Jiafeng Guo et al.ACL 2026

Builds on8

  1. MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained TransformersWenhui Wang, Furu Wei, Li Dong, Hangbo Bao et al.NeurIPS 2020 · 2,727 citations
  2. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTOmar Khattab, Matei ZahariaSIGIR 2020 · 1,246 citations
  3. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  4. Document Ranking with a Pretrained Sequence-to-Sequence ModelRodrigo Nogueira, Zhiying Jiang, Ronak Pradeep, Jimmy LinEMNLP Findings 2020 · 469 citations
  5. Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations

Related papers

  1. Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking ModelsJiawei Liu, Yangyang Kang, Di Tang, Kaisong Song et al.CCS 2022 · 22 citations
  2. Topic-oriented Adversarial Attacks against Black-box Neural Ranking ModelsYu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke et al.SIGIR 2023 · 20 citations
  3. Precisely the Point: Adversarial Augmentations for Faithful and Informative Text GenerationWenhao Wu, Wei Li, Jiachen Liu, Xinyan Xiao et al.EMNLP 2022 · 4 citations
  4. ``Someone Hid It!'': Query-Agnostic Black-Box Attacks on LLM-Based RetrievalJiate Li, Defu Cao, Li Li, Wei Yang et al.ICML 2026 · 4 citations
  5. Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-OffYu-An Liu, Ruqing Zhang, Mingkun Zhang, Wei Chen et al.AAAI 2024 · 17 citations
Dusk over the sea between two cliffs drawn in fine vertical lines