paper-with-me

홈 › Papers

Benchmarking LLAMA Model Security Against OWASP Top 10 For LLM Applications

2026-01-27 · Nourin Shahin, Izzat Alsmadi arxiv

As large language models (LLMs) move from research prototypes to enterprise systems, their security vulnerabilities pose serious risks to data privacy and system integrity. This study benchmarks various Llama model variants against the OWASP Top 10 for LLM Applications framework, evaluating threat detection accuracy, response safety, and computational overhead. Using the FABRIC testbed with NVIDIA A30 GPUs, we tested five standard Llama models and five Llama Guard variants on 100 adversarial prompts covering ten vulnerability categories. Our results reveal significant differences in security performance: the compact Llama-Guard-3-1B model achieved the highest detection rate of 76% with minimal latency (0.165s per test), whereas base models such as Llama-3.1-8B failed to detect threats (0% accuracy) despite longer inference times (0.754s). We observe an inverse relationship between model size and security effectiveness, suggesting that smaller, specialized models often outperform larger general-purpose ones in security tasks. Additionally, we provide an open-source benchmark dataset including adversarial prompts, threat labels, and attack metadata to support reproducible research in AI security, [1].

📄 PDF Abstract BibTeX arXiv:2601.19970

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mitigating the OWASP Top 10 For Large Language Models Applications using Intelligent Agents

2026-01-26 · Mohammad Fasha, Faisal Abul Rub, Nasim Matar, Bilal Sowan 외 arxiv

Large Language Models (LLMs) have emerged as a transformative and disruptive technology, enabling a wide range of applications in natural language processing, machine translation, and beyond. However, this widespread int…

Machine Translation

Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data

2025-05-15 · Adel ElZemity, Budi Arief, Shujun Li

The integration of large language models (LLMs) into cyber security applications presents significant opportunities, such as enhancing threat analysis and malware detection, but can also introduce critical risks and safe…

Malware DetectionSafety Alignment

Towards Unifying Quantitative Security Benchmarking for Multi Agent Systems

2025-07-23 · Gauri Sharma, Vidhi Kulkarni, Miles King, Ken Huang arxiv

Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces nov…

CyberLLMInstruct: A New Dataset for Analysing Safety of Fine-Tuned LLMs Using Cyber Security Data

2025-03-12 · Adel ElZemity, Budi Arief, Shujun Li

The integration of large language models (LLMs) into cyber security applications presents significant opportunities, such as enhancing threat analysis and malware detection, but can also introduce critical risks and safe…

Adversarial AttackMalware AnalysisMalware Detection

MCPThreatHive: Automated Threat Intelligence for Model Context Protocol Ecosystems

2026-04-15 · Yi Ting Shen, Kentaroh Toyoda, Alex Leung arxiv

The rapid proliferation of Model Context Protocol (MCP)-based agentic systems has introduced a new category of security threats that existing frameworks are inadequately equipped to address. We present MCPThreatHive, an …