paper-with-me

Papers

CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

2024-08-02 · Shengye Wan, Cyrus Nikolaidis, Daniel Song, David Molnar, James Crnkovich, Jayson Grace, Manish Bhatt, Sahana Chennabasappa, Spencer Whitman, Stephanie Ding, Vlad Ionescu, Yue Li, Joshua Saxe

We are releasing a new suite of security benchmarks for LLMs, CYBERSECEVAL 3, to continue the conversation on empirically measuring LLM cybersecurity risks and capabilities. CYBERSECEVAL 3 assesses 8 different risks across two broad categories: risk to third parties, and risk to application developers and end users. Compared to previous work, we add new areas focused on offensive security capabilities: automated social engineering, scaling manual offensive cyber operations, and autonomous offensive cyber operations. In this paper we discuss applying these benchmarks to the Llama 3 models and a suite of contemporaneous state-of-the-art LLMs, enabling us to contextualize risks both with and without mitigations in place.

📄 PDF Abstract BibTeX arXiv:2408.01605

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…

Similar Papers 제목 키워드 기반

Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

2023-12-07 · Manish Bhatt, Sahana Chennabasappa, Cyrus Nikolaidis, Shengye Wan 외

This paper presents CyberSecEval, a comprehensive benchmark developed to help bolster the cybersecurity of Large Language Models (LLMs) employed as coding assistants. As what we believe to be the most extensive unified c…

Language ModelingLanguage ModellingLarge Language Model

CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models

2024-04-19 · Manish Bhatt, Sahana Chennabasappa, Yue Li, Cyrus Nikolaidis 외

Large language models (LLMs) introduce new security risks, but there are few comprehensive evaluation suites to measure and reduce these risks. We present BenchmarkName, a novel benchmark to quantify LLM security risks a…

Rethinking CyberSecEval: An LLM-Aided Approach to Evaluation Critique

2024-11-13 · Suhas Hariharan, Zainab Ali Majid, Jaime Raldua Veuthey, Jacob Haimes

A key development in the cybersecurity evaluations space is the work carried out by Meta, through their CyberSecEval approach. While this work is undoubtedly a useful contribution to a nascent field, there are notable fe…

LLM Cyber Evaluations Don't Capture Real-World Risk

2025-01-31 · Kamilė Lukošiūtė, Adam Swanda

Large language models (LLMs) are demonstrating increasing prowess in cybersecurity applications, creating creating inherent risks alongside their potential for strengthening defenses. In this position paper, we argue tha…

Adversarial Arena: Crowdsourcing Data Generation through Interactive Competition

2026-04-20 · Prasoon Goyal, Sattvik Sahai, Michael Johnston, Hangjie Shi 외 arxiv

Post-training Large Language Models requires diverse, high-quality data which is rare and costly to obtain, especially in low resource domains and for multi-turn conversations. Common solutions are crowdsourcing or synth…

Code Generation