mlsanityData to 14 Oct 2026

Special-Character Adversarial Attacks on Open-Source Language Model

arXiv 2508.14070 ↗First posted 12 Aug 2025cs.CR cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have achieved remarkable performance across diverse natural language processing tasks, yet their vulnerability to character-level adversarial manipulations presents significant security challenges for real-world deployments. This paper presents a study of different special character attacks including unicode, homoglyph, structural, and textual encoding attacks aimed at bypassing safety mechanisms. We evaluate seven prominent open-source models ranging from 3.8B to 32B parameters on 4,000+ attack attempts. These experiments reveal critical vulnerabilities across all model sizes, exposing failure modes that include successful jailbreaks, incoherent outputs, and unrelated hallucinations.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 15 of its 31 references that are in the map. First posted on arXiv 12 Aug 2025.

Builds on

15 of 31 references.

References · 15

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2017Deep reinforcement learning from human preferencescited by 3,912
  5. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  6. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  7. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  8. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Modelscited by 785
  9. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
  10. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 639
  11. 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 571
  12. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 381
3 more
  1. 2019Combating Adversarial Misspellings with Robust Word Recognitioncited by 163
  2. 2023Fundamental Limitations of Alignment in Large Language Modelscited by 155
  3. 2023Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMscited by 124

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 6.

7 papers.

  1. 2026VoxSafeBench: Not Just What Is Said, but Who, How, and Wherecited by 8
  2. 2026Adversarial News and Lost Profits: Manipulating Headlines in LLM-Driven Algorithmic Tradingcited by 4
  3. 2025Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intentcited by 2
  4. 2026StressWeb: A Diagnostic Benchmark for Web Agent Robustness under Realistic Interaction Variabilitycited by 2
  5. 2026A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combinationcited by 0
  6. 2026Build it, Break it, Repeat: Benchmarking and improving LLM-manipulated disinformation detection in social media postscited by 0
  7. 2026Quad-State Safety Evaluation of Open-Weight Large Language Models on Non-Canonical Inputscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks
  2. 2024Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models
  3. 2025Evaluating Adversarial Vulnerabilities in Modern Large Language Models
  4. 2025The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models
  5. 2025Safeguarding Efficacy in Large Language Models: Evaluating Resistance to Human-Written and Algorithmic Adversarial Prompts
  6. 2026Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey
  7. 2025Attack and defense techniques in large language models: A survey and new perspectives
  8. 2024Impact of Non-Standard Unicode Characters on Security and Comprehension in Large Language Models