mlsanityData to 7 Oct 2026

Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking Models

arXiv 2412.18770 ↗First posted 25 Dec 2024cs.IRcited by 6

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

Neural ranking models (NRMs) have been shown to be highly effective in terms of retrieval performance. Unfortunately, they have also displayed a higher degree of sensitivity to attacks than previous generation models. To help expose and address this lack of robustness, we introduce a novel ranking attack framework named Attack-in-the-Chain, which tracks interactions between large language models (LLMs) and NRMs based on chain-of-thought (CoT) prompting to generate adversarial examples under black-box settings. Our approach starts by identifying anchor documents with higher ranking positions than the target document as nodes in the reasoning chain. We then dynamically assign the number of perturbation words to each node and prompt LLMs to execute attacks. Finally, we verify the attack performance of all nodes at each reasoning step and proceed to generate the next reasoning step. Empirical results on two web search benchmarks show the effectiveness of our method.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 25 of its 41 references that are in the map. First posted on arXiv 25 Dec 2024.

Builds on

25 of 41 references.

References · 25

  1. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  2. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  3. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  4. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  5. 2023Measuring Faithfulness in Chain-of-Thought Reasoningcited by 668
  6. 2019Passage Re-ranking with BERTcited by 629
  7. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  8. 2020Overview of the TREC 2019 deep learning trackcited by 282
  9. 2017A Deep Relevance Matching Model for Ad-hoc Retrievalcited by 126
  10. 2024Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessmentcited by 117
  11. 2019Deeper Text Understanding for IR with Contextual Neural Language Modelingcited by 111
  12. 2023An LLM can Fool Itself: A Prompt-Based Adversarial Attackcited by 111
13 more
  1. 2024AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attackscited by 94
  2. 2023Improving Language Models via Plug-and-Play Retrieval Feedbackcited by 87
  3. 2022PRADA: Practical Black-Box Adversarial Attacks against Neural Ranking Modelscited by 44
  4. 2024Puzzle Solving using Reasoning of Large Language Models: A Surveycited by 44
  5. 2020Adversarial Semantic Collisionscited by 42
  6. 2020PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrievalcited by 40
  7. 2022Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Modelscited by 37
  8. 2024A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Sciencecited by 31
  9. 2020One word at a time: adversarial attacks on retrieval modelscited by 23
  10. 2023Topic-oriented Adversarial Attacks against Black-box Neural Ranking Modelscited by 18
  11. 2023Towards Imperceptible Document Manipulations against Neural Ranking Modelscited by 18
  12. 2022BERT Rankers are Brittle: a Study using Adversarial Document Perturbationscited by 16
  13. 2023Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Offcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systemscited by 10
  2. 2026Ranked by Position: Order Sensitivity as an Exploitable Attack Surface in LLM Listwise Recommenderscited by 1
  3. 2026One Word is Enough: Minimal Adversarial Perturbations for Neural Text Rankingcited by 0
  4. 2026Can LLMs Fool Graph Learning? Exploring Universal Adversarial Attacks on Text-Attributed Graphscited by 0
  5. 2026Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Modelscited by 0
  6. 2026VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
  2. 2024Enhancing Adversarial Attacks through Chain of Thought
  3. 2024Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models
  4. 2025Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models
  5. 2025Selective Adversarial Attacks on LLM Benchmarks
  6. 2026Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
  7. 2025Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment
  8. 2026"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval