Pasta Lab 加入 Artificial Analysis Cyber Index 联盟
做安全评测的可以关注，Pasta Lab 带着他们搞逆向工程评测的 SRE-Bench 经验加入了 Artificial Analysis 的网络安全基准联盟。
Pasta Lab 宣布加入 Artificial Analysis Cyber Index Alliance，参与 AI 网络安全基准的制定。Pasta Lab 是一支由 Columbia University、Tufts University 和 UCLA 成员组成的研究团队，此前开发了评估 AI 逆向工程能力的 SRE-Bench。Cyber Index Alliance 现有成员包括 CollinearAI、IBM、NVIDIA 和 Vercel，共同推进 Artificial Analysis Cyber Index 对 AI 模型在真实网络安全任务上的评测。
Pasta Lab has joined the Artificial Analysis Cyber Index Alliance, to help shape the future of AI cybersecurity benchmarking
Pasta Lab is a research group with members from Columbia University, Tufts University, and UCLA, specializing in AI and security research. The group also developed SRE-Bench, a benchmark evaluating AI capabilities in reverse engineering.
We look forward to collaborating with Pasta Lab, along side our current Alliance members @CollinearAI, @IBM, @nvidia, and @vercel, to further develop the Artificial Analysis Cyber Index and advance the evaluation of AI models on real-world cybersecurity tasks.
Organizations working on AI Cybersecurity evaluations interested in joining the Cyber Index Alliance can contact us at [email protected]
