Special-Character Adversarial Attacks on Open-Source Language Model
Fuente:
arXiv
Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911287116562432 |
|---|---|
| author | Sarabamoun, Ephraiem |
| author_facet | Sarabamoun, Ephraiem |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14070 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Special-Character Adversarial Attacks on Open-Source Language Model Sarabamoun, Ephraiem Cryptography and Security Artificial Intelligence 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. |
| title | Special-Character Adversarial Attacks on Open-Source Language Model |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2508.14070 |