Fri. Mar 29th, 2024

Content Assessment: From Taxonomies to Threats? Securing Machine Learning Algorithms

Information - 97%
Insight - 95%
Relevance - 92%
Objectivity - 93%
Authority - 96%

95%

Excellent

A short percentage-based assessment of the qualitative benefit of the recently published ENISA report on securing machine learning algorithms.

Editor’s Note: The European Union Agency for Cybersecurity, ENISA, is the Union’s agency dedicated to achieving a high common level of cybersecurity across Europe. In December of 2021, ENISA published Securing Machine Algorithms, a report that presents a taxonomy of machine learning techniques and core functionalities as well as a mapping of threats targeting machine learning techniques and the vulnerabilities of machine learning algorithms. This new report may be beneficial for cybersecurity, information governance, and legal discovery professionals operating in the eDiscovery ecosystem as they consider cyber discovery through the lens of increasing cyber threats.


Press Announcement And Report*

Artificial Intelligence: How to Make Machine Learning Cyber Secure

Machine learning (ML) is currently the most developed and the most promising subfield of artificial intelligence for industrial and government infrastructures. By providing new opportunities to solve decision-making problems intelligently and automatically, artificial intelligence (AI) is applied in almost all sectors of our economy.

While the benefits of AI are significant and undeniable, the development of AI also induces new threats and challenges, identified in the ENISA AI Threat Landscape.

Machine learning algorithms are used to give machines the ability to learn from data in order to solve tasks without being explicitly programmed to do so. However, such algorithms need extremely large volumes of data to learn. And because they do, they can also be subjected to specific cyber threats.

The Securing Machine Learning Algorithms report presents a taxonomy of ML techniques and core functionalities. The report also includes a mapping of the threats targeting ML techniques and the vulnerabilities of ML algorithms. It provides a list of relevant security controls recommended to enhance cybersecurity in systems relying on ML techniques. One of the challenges highlighted is how to select the security controls to apply without jeopardizing the expected level of performance.

The mitigation controls for ML-specific attacks outlined in the report should in general be deployed during the entire lifecycle of systems and applications making use of ML.

Machine Learning Algorithms Taxonomy

Based on desk research and interviews with the experts of the ENISA AI ad-hoc working group, a total of 40 most commonly used ML algorithms were identified. The taxonomy developed is based on the analysis of such algorithms.

The non-exhaustive taxonomy devised is to support the process of identifying which specific threats target ML algorithms, what are the associated vulnerabilities, and the security controls needed to address those vulnerabilities.

Target Audience

  • Public/government: EU institutions & agencies, regulatory bodies of Member States, supervisory authorities in data protection, military and intelligence agencies, law enforcement community, international organizations, and national cybersecurity authorities.
  • Industry at large including small & medium enterprises (SMEs) resorting to AI solutions, operators of essential services ;
  • AI technical, academic and research community, AI cybersecurity experts, and AI experts such as designers, developers, ML experts, data scientists, etc.
  • Standardization bodies.

Background

The EU Agency for Cybersecurity continues to play a bigger role in the assessment of Artificial Intelligence (AI) by providing key input for future policies. The Agency takes part in the open dialogue with the European Commission and EU institutions on AI cybersecurity and regulatory initiatives to this end.

The Agency set up the ENISA Ad Hoc Working Group on Cybersecurity for Artificial Intelligence last year. The working group supports ENISA in the process of building knowledge on AI Cybersecurity. Members of the group come from the European Commission Directorate-General Communications Networks, Content and Technology (DG CONNECT), the European Commission Directorate-General Joint Research Committee (DG JRC), Europol, the European Defence Agency (EDA), the European Union Agency for the Operational Management of Large-Scale IT Systems in the Area of Freedom, Security and Justice (eu-LISA), the European Telecommunications Standards Institute (ETSI), as well as academics and industry experts.

Further Information

Read the original announcement.


Read the Complete Report: Securing Machine Learning Algorithms (PDF) – Mouseover to Scroll

ENISA Report - Securing Machine Learning Algorithms

Original Submission: The European Union Agency for Cybersecurity, 2021. Securing Machine Learning Algorithms. [online] Attiki: ENISA. Available at: <https://www.enisa.europa.eu/publications/securing-machine-learning-algorithms> [Accessed 21 December 2021].

*Shared with permission under Creative Commons – Attribution 4.0 International (CC BY 4.0) – license.


Additional Reading

Source: ComplexDiscovery

 

Generative Artificial Intelligence and Large Language Model Use

ComplexDiscovery OÜ recognizes the value of GAI and LLM tools in streamlining content creation processes and enhancing the overall quality of its research, writing, and editing efforts. To this end, ComplexDiscovery OÜ regularly employs GAI tools, including ChatGPT, Claude, Midjourney, and DALL-E, to assist, augment, and accelerate the development and publication of both new and revised content in posts and pages published (initiated in late 2022).

ComplexDiscovery also provides a ChatGPT-powered AI article assistant for its users. This feature leverages LLM capabilities to generate relevant and valuable insights related to specific page and post content published on ComplexDiscovery.com. By offering this AI-driven service, ComplexDiscovery OÜ aims to create a more interactive and engaging experience for its users, while highlighting the importance of responsible and ethical use of GAI and LLM technologies.

 

Have a Request?

If you have information or offering requests that you would like to ask us about, please let us know, and we will make our response to you a priority.

ComplexDiscovery OÜ is a highly recognized digital publication focused on providing detailed insights into the fields of cybersecurity, information governance, and eDiscovery. Based in Estonia, a hub for digital innovation, ComplexDiscovery OÜ upholds rigorous standards in journalistic integrity, delivering nuanced analyses of global trends, technology advancements, and the eDiscovery sector. The publication expertly connects intricate legal technology issues with the broader narrative of international business and current events, offering its readership invaluable insights for informed decision-making.

For the latest in law, technology, and business, visit ComplexDiscovery.com.