mlsanityData to 14 Oct 2026

Adversarial Semantic Collisions

arXiv 2011.04743 ↗First posted 9 Nov 2020cs.CL cs.CRcited by 42

Not on the map. Why?

Abstract (arXiv)

We study semantic collisions: texts that are semantically unrelated but judged as similar by NLP models. We develop gradient-based approaches for generating semantic collisions and demonstrate that state-of-the-art models for many tasks which rely on analyzing the meaning and similarity of texts-- including paraphrase identification, document retrieval, response suggestion, and extractive summarization-- are vulnerable to semantic collisions. For example, given a target query, inserting a crafted collision into an irrelevant document can shift its retrieval rank from 1000 to top 3. We show how to generate semantic collisions that evade perplexity-based filtering and discuss other potential mitigations. Our code is available at https://github.com/csong27/collision-bert.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 11; 2024: 10; 2025: 6; 2026: 7.

42 papers.

Sort:

By area:

  1. 2023FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Promptscited by 398
  2. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 192
  3. 2023Poisoning Retrieval Corpora by Injecting Adversarial Passagescited by 159
  4. 2023Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMscited by 124
  5. 2024Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documentscited by 102
  6. 2021Hidden Backdoors in Human-Centric Language Modelscited by 90
  7. 2021Controlled Text Generation as Continuous Optimization with Multiple Constraintscited by 70
  8. 2022Gradient-Based Constrained Sampling from Language Modelscited by 64
  9. 2024"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Modelscited by 60
  10. 2022Describing Differences between Text Distributions with Natural Languagecited by 54
  11. 2022Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Modelscited by 37
  12. 2023Mass-Producing Failures of Multimodal Systems with Language Modelscited by 36
30 more
  1. 2025Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Modelscited by 33
  2. 2023Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Methodcited by 29
  3. 2023Adversarial Illusions in Multi-Modal Embeddingscited by 29
  4. 2025FlippedRAG: Black-Box Opinion Manipulation Adversarial Attacks to Retrieval-Augmented Generation Modelscited by 25
  5. 2024Corpus Poisoning via Approximate Greedy Gradient Descentcited by 21
  6. 2023A Survey on Out-of-Distribution Evaluation of Neural NLP Modelscited by 20
  7. 2024GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Searchcited by 20
  8. 2023Towards Imperceptible Document Manipulations against Neural Ranking Modelscited by 18
  9. 2024Rag and Roll: An End-to-End Evaluation of Indirect Prompt Manipulations in LLM-based Application Frameworkscited by 17
  10. 2021Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluationcited by 16
  11. 2024Adversarial Decoding: Generating Readable Documents for Adversarial Objectivescited by 16
  12. 2026Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systemscited by 16
  13. 2024Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspectivecited by 15
  14. 2024Multi-granular Adversarial Attacks against Black-box Neural Ranking Modelscited by 14
  15. 2022Paraphrase Identification with Deep Learning: A Review of Datasets and Methodscited by 13
  16. 2024Black-Box Opinion Manipulation Attacks to Retrieval-Augmented Generation of Large Language Modelscited by 11
  17. 2025Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrievalcited by 11
  18. 2025Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attackcited by 10
  19. 2023MAWSEO: Adversarial Wiki Search Poisoning for Illicit Online Promotioncited by 7
  20. 2025Reproducing HotFlip for Corpus Poisoning Attacks in Dense Retrievalcited by 7
  21. 2022Redwood: Using Collision Detection to Grow a Large-Scale Intent Classification Datasetcited by 6
  22. 2024Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking Modelscited by 6
  23. 2026ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Modelscited by 5
  24. 2023Defense of Adversarial Ranking Attack in Text Retrieval: Benchmark and Baseline via Detectioncited by 3
  25. 2025RobustMask: Certified Robustness against Adversarial Neural Ranking Attack via Randomized Maskingcited by 1
  26. 2026SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoningcited by 1
  27. 2026Statistically Undetectable Backdoors in Deep Neural Networkscited by 1
  28. 2026TriShieldRAG: 3 Rings, One Blind Spot in Layered Defenses for Retrieval-Augmented Generationcited by 0
  29. 2026Coverage Is Not Containment: A Fundamental Limit of Admission-Time Defenses Against Coordinated Poisoning of Vector Retrievalcited by 0
  30. 2026VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Modelscited by 0