paper-with-me

Papers

LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges

2025-06-09 · Haoyang Li, Huan Gao, Zhiyuan Zhao, Zhiyu Lin, Junyu Gao, Xuelong Li

The widespread adoption of Large Language Models (LLMs) has heightened concerns about their security, particularly their vulnerability to jailbreak attacks that leverage crafted prompts to generate malicious outputs. While prior research has been conducted on general security capabilities of LLMs, their specific susceptibility to jailbreak attacks in code generation remains largely unexplored. To fill this gap, we propose MalwareBench, a benchmark dataset containing 3,520 jailbreaking prompts for malicious code-generation, designed to evaluate LLM robustness against such threats. MalwareBench is based on 320 manually crafted malicious code generation requirements, covering 11 jailbreak methods and 29 code functionality categories. Experiments show that mainstream LLMs exhibit limited ability to reject malicious code-generation requirements, and the combination of multiple jailbreak methods further reduces the model's security capabilities: specifically, the average rejection rate for malicious content is 60.93%, dropping to 39.92% when combined with jailbreak attack algorithms. Our work highlights that the code security capabilities of LLMs still pose significant challenges.

📄 PDF Abstract BibTeX arXiv:2506.10022

Code (1)

MAIL-Tele-AI/MalwareBench 공식 구현

Tasks

Code Generation

Similar Papers 제목 키워드 기반

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

2024-10-11 · Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas 외

The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as simple chatbots. Meanwhile, LLM agents --…

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters

2024-07-02 · Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang 외

The widespread applications of large language models (LLMs) have brought about concerns regarding their potential misuse. Although aligned with human preference data before release, LLMs remain vulnerable to various mali…

Red TeamingSafety Alignment

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs

2026-05-18 · Wenzhuo Xu, Zhipeng Wei, Zonghao Ying, Deyue Zhang 외 arxiv

Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-image inputs, inadvertently introducing new vulnerabilities due to les…

Visual Reasoning

Auto-Tuning Safety Guardrails for Black-Box Large Language Models

2025-12-14 · Perry Abdulkadir arxiv

Large language models (LLMs) are increasingly deployed behind safety guardrails such as system prompts and content filters, especially in settings where product teams cannot modify model weights. In practice these guardr…

Hyperparameter Optimization

Does Refusal Training in LLMs Generalize to the Past Tense?

2024-07-16 · Maksym Andriushchenko, Nicolas Flammarion

Refusal training is widely used to prevent LLMs from generating harmful, undesirable, or illegal outputs. We reveal a curious generalization gap in the current refusal training approaches: simply reformulating a harmful …