paper-with-me

홈 › Papers

Special-Character Adversarial Attacks on Open-Source Language Model

2025-08-12 · Ephraiem Sarabamoun 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.

📄 PDF Abstract BibTeX arXiv:2508.14070

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Every Character Counts: From Vulnerability to Defense in Phishing Detection

2025-09-24 · Maria Chiper, Radu Tudor Ionescu arxiv

Phishing attacks targeting both organizations and individuals are becoming an increasingly significant threat as technology advances. Current automatic detection methods often lack explainability and robustness in detect…

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

2020-09-05 · Nilaksh Das, Haekyu Park, Zijie J. Wang, Fred Hohman 외

Deep neural networks (DNNs) are now commonly used in many domains. However, they are vulnerable to adversarial attacks: carefully crafted perturbations on data inputs that can fool a model into making incorrect predictio…

Unsourced Adversarial CAPTCHA: A Bi-Phase Adversarial CAPTCHA Framework

2025-06-12 · Xia Du, Xiaoyuan Liu, Jizhe Zhou, Zheng Lin 외

With the rapid advancements in deep learning, traditional CAPTCHA schemes are increasingly vulnerable to automated attacks powered by deep neural networks (DNNs). Existing adversarial attack methods often rely on origina…

Adversarial AttackDiversityLanguage ModelingLanguage Modelling+1

Adversarial Examples in the Physical World: A Survey

2023-11-01 · Jiakai Wang, Xianglong Liu, Jin Hu, Donghua Wang 외

Deep neural networks (DNNs) have demonstrated high vulnerability to adversarial examples, raising broad security concerns about their applications. Besides the attacks in the digital world, the practical implications of …

Survey

AdversariaLib: An Open-source Library for the Security Evaluation of Machine Learning Algorithms Under Attack

2016-11-15 · Igino Corona, Battista Biggio, Davide Maiorca

We present AdversariaLib, an open-source python library for the security evaluation of machine learning (ML) against carefully-targeted attacks. It supports the implementation of several attacks proposed thus far in the …

BIG-bench Machine LearningGeneral Classification