小程序
传感搜
传感圈

NCSC publishes ‘vague’ security principles for machine learning models

2022-09-13
关注

The UK’s National Cyber Security Centre (NCSC) has published a set of security principles for developers and companies implementing machine learning models. An ML specialist who spoke to Tech Monitor said the principles represent a positive direction of travel but are “vague” when it comes to details.

The principles set out by the NCSC provide a ‘direction of travel’ rather than specific instructions. (Photo by gorodenkoff/iStock)

The NCSC has developed its security principles as the role of machine learning and artificial intelligence is growing in industry and wider society, from the AI assistant in smartphones to the use of machine learning in healthcare. The most recent IBM Global AI Adoption Index found that 35% of companies reported using AI in their business, and an additional 42% reported they are exploring AI.

The NCSC says that as the use of machine learning grows it is important for users to know it is being deployed securely and not putting personal safety or data at risk. “It turns out this is really hard,” the agency said in a blog post. “It was these challenges, many of which don’t have simple solutions, that motivated us to develop actionable guidance in the form of our principles.”

Doing so involved looking at techniques and defences against potential security flaws, but also taking a more pragmatic approach and finding actionable ways of protecting machine learning systems from exploitation in a real-world environment.

Companies Intelligence

View All

Reports

View All

Data Insights

View All

The nature of machine learning models, which sees them evolve through automatically analysing data, means they are difficult to secure. “Since a model’s internal logic relies on data, its behaviour can be difficult to interpret, and it’s often challenging (or even impossible) to fully understand why it’s doing what it’s doing,” the NCSC blog says.

This means many machine learning components are being deployed in networks and systems without the same high level of security found in non-automated tools, leaving large parts of the system inaccessible to cybersecurity professionals. This in turn is causing some vulnerabilities to be missed and exposes the system to attack and is also introducing more vulnerabilities that are inherent in machine learning and are present throughout all stages of the machine learning lifecycle.

Lack of transparency in machine learning models

The group of attacks that are designed to exploit these inherent issues in machine learning are known as “adversarial machine learning” (AML) and understanding them requires knowledge of multiple disciplines including data science, cybersecurity, and software development.

The NCSC produced a set of security principles for systems containing ML components with the goal of bringing awareness of AML attacks and defences to anyone involved in the development, deployment or decommissioning of a system containing ML. The logic used by ML models and data used to train the models can often be opaque, leaving security experts in the dark when it comes to inspecting them for security flaws.

Content from our partners

How collaborative automation can accelerate digital transformation

Are you ready to respond to the latest cyber threats in education?

A blueprint for solving merger and acquisition HR challenges

The principles suggest designing for security when drafting system requirements, securing the supply chain and making sure data comes from a trusted source and securing infrastructure by applying trust controls to anything and anyone that enters the development environment.

Assets need to be tracked through the creation of documentation covering the creation, operation and lifecycle management of models and datasets, and ensuring the model architecture is designed for security.

Data, insights and analysis delivered to you View all newsletters By The Tech Monitor team Sign up to our newsletters

“ML doesn't necessarily pose any more danger than any other piece of logic in a software system but there are a few nuances to ML models that should be appreciated,” says Nigel Cannings, the founder of compliance solution company Intelligent Voice.

“An ML system is built on data, the finished system represents valuable intellectual property and in some cases, the data used to train it is also something that is often needed to be protected.”

This mirrors the concerns raised by the NCSC which said that without open information on the data used to train machine learning algorithms or the methods it uses to make its findings, it is difficult to spot vulnerabilities that could expose the system.

However, Cannings warns that while the NCSC principles are a positive move, the lack of detail makes them less useful as a tool for communicating potential risks. “The principles in the NCSC are vague, and provide general guidelines with much borrowed from conventional software cybersecurity," he says. "They are not wrong and point to the importance of education of developers and data scientists but more detail could have been provided to communicate the risks."

NCSC ML security principles 'a direction of travel'

Developers and admins are likely to take steps to protect their models if they are aware of the risks they can expose, explains Canning, adding that “in the same way software engineering has evolved to be increasingly more security conscious, ML and MLOps will benefit from this practice too.”

The NCSC principles are more a “direction of travel” than a set of guidelines or blueprint to follow, he says, and the exact measures taken will vary by model and change with research.

Todd R Weiss, an analyst for Futurum Research adds: “It is wise to consider all aspects of security when it comes to AI and ML, even while both technologies can also help companies address and solve technology challenges. Like so many things in life, AI and ML are also double-edged swords that can bring huge benefits as well as harm. Those concerns must be balanced with their benefits as part of an overall IT infrastructure and business strategy.”

Despite these inherent risks, Weiss said AI and ML are “far more beneficial and useful as technologies in our world”. He argues: “Without AI and ML, incredibly powerful digital twins would not be possible, medical breakthroughs would not be happening and fledgling metaverse communities would not be possible. There are many other examples of the benefits of AI and ML, and there will always be bad actors searching for ways to cause havoc in all forms of technology."

Weiss praised the NCSC for its ML security principles as they will “encourage awareness, acceptance, and critical thinking about these ongoing concerns and can actively help businesses truly take these matters to heart when using and exploring AI and ML”.

Read more: Meta has questions to answer about its responsible AI plans

Topics in this article: AI, Cybersecurity

参考译文
NCSC发布了机器学习模型的“模糊”安全原则
英国国家网络安全中心(NCSC)为实现机器学习模型的开发人员和公司发布了一套安全原则。一位ML专家在接受Tech Monitor采访时表示,这些原则代表了一个积极的发展方向,但涉及到细节时显得“模糊”。随着机器学习和人工智能在工业和更广泛的社会中的作用日益增长,从智能手机中的人工智能助手到机器学习在医疗保健中的使用,NCSC制定了其安全原则。最新的IBM全球人工智能采用指数发现,35%的公司报告在其业务中使用了人工智能,另有42%的公司报告称他们正在探索人工智能。NCSC表示,随着机器学习使用的增长,重要的是让用户知道它是安全部署的,不会危及个人安全或数据。“事实证明,这真的很难,”该机构在一篇博客文章中说。“正是这些挑战,其中许多都没有简单的解决方案,促使我们以原则的形式制定出可操作的指导方针。”这样做需要研究针对潜在安全缺陷的技术和防御措施,但也需要采取更务实的方法,并找到可操作的方法来保护机器学习系统在现实环境中不被利用。机器学习模型的本质是通过自动分析数据来发展,这意味着它们很难安全。NCSC的博客写道:“由于模型的内部逻辑依赖于数据,它的行为可能很难解释,而且通常很难(甚至不可能)完全理解它为什么这样做。”这意味着,许多机器学习组件被部署在网络和系统中,却没有非自动化工具中所具有的高级别安全性,导致网络安全专业人员无法访问系统的大部分内容。这反过来又会导致一些漏洞被遗漏,使系统容易受到攻击,还会引入更多机器学习中固有的漏洞,这些漏洞会出现在机器学习生命周期的所有阶段。旨在利用机器学习中这些固有问题的攻击组被称为“对抗性机器学习”(AML),理解它们需要多个学科的知识,包括数据科学、网络安全和软件开发。NCSC为包含ML组件的系统制定了一套安全原则,目的是让参与包含ML系统的开发、部署或退役的任何人都能意识到AML攻击和防御。ML模型使用的逻辑和用于训练模型的数据通常是不透明的,让安全专家在检查它们的安全缺陷时处于黑暗之中。这些原则建议在起草系统需求时进行安全设计,确保供应链的安全,确保数据来自可信的来源,并通过对进入开发环境的任何事物和任何人应用信任控制来保护基础设施。资产需要通过文档的创建来跟踪,文档涵盖了模型和数据集的创建、操作和生命周期管理,并确保模型架构是为安全而设计的。合规解决方案公司Intelligent Voice的创始人奈吉尔•坎宁斯表示:“ML并不一定比软件系统中的任何其他逻辑块更危险,但ML模型有一些细微差别应该得到重视。”“一个ML系统是建立在数据之上的,完成的系统代表着有价值的知识产权,在某些情况下,用于训练它的数据也是需要保护的。” 这反映了NCSC提出的担忧,该机构表示,如果不公开用于训练机器学习算法的数据信息,或者不公开用于得出结论的方法,就很难发现可能暴露系统的漏洞。然而,坎宁斯警告说,尽管NCSC原则是一个积极的举措,但缺乏细节使其作为沟通潜在风险的工具不那么有用。NCSC的原则是模糊的,并且提供了从传统软件网络安全借鉴的通用指南,"他说。"他们没有错,指出了教育开发人员和数据科学家的重要性,但可以提供更多的细节来沟通风险。"开发人员和管理员很可能采取措施来保护他们的模型,如果他们意识到他们可以暴露的风险,Canning解释说,并补充说,“以同样的方式,软件工程已经进化到越来越多的安全意识,ML和mlop将从这种实践中受益。”他说,NCSC的原则更像是一个“前进的方向”,而不是一套可以遵循的指导方针或蓝图,具体的措施将因模型而异,并随着研究的变化而变化。Futurum Research的分析师Todd R Weiss补充道:“当涉及到AI和ML时,考虑到安全的所有方面是明智的,尽管这两种技术也可以帮助公司解决技术挑战。就像生活中的许多事情一样,AI和ML也是双刃剑,既能带来巨大的好处,也能带来巨大的伤害。作为整体IT基础设施和业务策略的一部分,必须平衡这些关注点与它们的好处。Weiss说,尽管存在这些固有的风险,人工智能和ML“作为技术在我们的世界中更有益、更有用”。他认为:“如果没有人工智能和人工智能,就不可能出现强大得令人难以置信的数字双胞胎,也不可能出现医学突破,也不可能出现初具雏形的元宇宙社区。还有许多其他例子可以证明AI和ML的好处,而且总是会有坏人寻找方法对所有形式的技术造成破坏。Weiss赞扬NCSC的ML安全原则,因为它们将“鼓励人们对这些持续关注的问题的认识、接受和批判性思考,并可以积极帮助企业在使用和探索AI和ML时真正把这些问题放在心里”。
您觉得本篇内容如何
评分

评论

您需要登录才可以回复|注册

提交评论

提取码
复制提取码
点击跳转至百度网盘