arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.19310cs.CRcs.AI
收藏

Model X-Ray: 使用少样本学习检测AI模型权重中的隐藏恶意软件

Model X-Ray: Detection of Hidden Malware in AI Model Weights using Few Shot Learning

Department of Computer Science and Ariel Cyber Innovation Center, Ariel University(计算机科学系和 Ariel 网络创新中心,阿里尔大学);Department of Computer and Software Engineering and Ariel Cyber Innovation Center, Ariel University(计算机与软件工程系和 Ariel 网络创新中心,阿里尔大学)

Daniel Gilkarov, Ran Dubin

AI总结:

本文提出一种基于少样本学习的AI模型恶意软件检测方法,通过将模型权重转换为图像表示,仅需6个训练样本即可检测低至6%嵌入率的隐蔽攻击,并展现出对新型扩频隐写攻击的鲁棒性。

摘要:

随着人工智能(AI)的快速发展和Model Zoo等共享AI模型平台的广泛使用,AI模型被利用的潜在风险增加。攻击者可以通过隐写技术将恶意软件嵌入AI模型中,利用这些模型庞大的体积隐藏恶意数据并用于恶意目的,例如远程代码执行。确保AI模型的安全性是一个新兴的研究领域,对于保护依赖AI技术的众多组织和用户至关重要。本研究利用成熟的图像少样本学习技术,通过一种新颖的图像表示将AI模型转换到图像领域。在该领域应用少样本学习使我们能够创建实用的模型,这是先前工作所缺乏的。我们的方法解决了现有最先进检测技术中阻碍其实用性的关键限制。该方法将所需的训练数据集大小从40000个模型减少到仅6个。此外,我们的方法能够持续检测嵌入率低至25%甚至在某些情况下低至6%的隐蔽攻击,而先前的工作仅被证明对100%-50%的嵌入率有效。我们采用严格的评估策略,确保训练后的模型在各种因素下具有泛化能力。此外,我们展示了训练后的模型成功检测到新型扩频隐写攻击,仅通过学习一种攻击类型就证明了模型令人印象深刻的鲁棒性。我们开源代码以支持可重复性并促进这一新领域的研究。

英文摘要:

The potential for exploitation of AI models has increased due to the rapid advancement of Artificial Intelligence (AI) and the widespread use of platforms like Model Zoo for sharing AI models. Attackers can embed malware within AI models through steganographic techniques, taking advantage of the substantial size of these models to conceal malicious data and use it for nefarious purposes, e.g. Remote Code Execution. Ensuring the security of AI models is a burgeoning area of research essential for safeguarding the multitude of organizations and users relying on AI technologies. This study leverages well-studied image few-shot learning techniques by transferring the AI models to the image field using a novel image representation. Applying few-shot learning in this field enables us to create practical models, a feat that previous works lack. Our method addresses critical limitations in state-of-the-art detection techniques that hinder their practicality. This approach reduces the required training dataset size from 40000 models to just 6. Furthermore, our methods consistently detect delicate attacks of up to 25% embedding rate and even up to 6% in some cases, while previous works were only shown to be effective for a 100%-50% embedding rate. We employ a strict evaluation strategy to ensure the trained models are generic concerning various factors. In addition, we show that our trained models successfully detect novel spread-spectrum steganography attacks, demonstrating the models' impressive robustness just by learning one type of attack. We open-source our code to support reproducibility and enhance the research in this new field.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑