About Us | Contact Us
View Cart

When New Technology Brings New Risk

By Vigilize | Monday, May 17, 2021 - Leave a Comment

Machine learning is here to stay, so how do we assess its risk?


An article review.


When it comes to assessing technology risk, there seems to be as many methods as there are attack vectors… but what happens when an entirely new field opens up?  When it comes to machine learning (ML) there aren’t many methodologies available, but a team of Microsoft employees are working on changing that.  The team in question is working on Counterfeit, a tool for assessing the security of ML systems, and in addition to creating this command-line tool they have written some interesting guidance on how you can begin to assess ML risk on your own.

The guidance includes a brief description of the ML development lifecycle, which begins with collecting the data which will be used to train the model and continues through processing that data, feeding it to the ML algorithm, validating its output and finally putting the system into production.  Once the system is in production the job isn’t over, though: ML algorithms must be continuously monitored to ensure their output remains valid.

In addition to needing to ensure the ML system is producing valid output, a number of attacks exist that could reveal the data the model was trained with.  If the model in question was trained with personally identifiable information (PII), this could raise questions regarding compliance with standards such as HIPPA or GLBA.

Finally, the guidance looks at the methodology behind potential ML attacks.  Starting with information gathering about the application, an attacker may then focus on attacking the ML algorithm itself, either to reveal data or to repurpose the algorithm to perform a potentially malicious task.  It’s also important to realize that while ML is new, it is still a component of your existing technology infrastructure.  Therefore all the traditional technology risks are also present, and a compromised workstation or server could also lead to a potential compromise of the ML system.

Machine learning offers tantalizing potential benefits, but as it is a rapidly developing technology one must also stay ahead of the curve when it comes to new threats.  Luckily frameworks like the one provided by the Azure team are being developed to assess those risks, and it certainly won’t be the last.


Original article by the Microsoft Azure Team.


same_strip_012513


 

Posted in Article Reviews

Latest News
    Another awareness poster for YOUR customers (and users).  Now that we have our own employees aware, maybe it’s time to start posting content for our customers! Download the large versions here: Awareness Poster (Portrait) Awareness Poster (Landscape)   You are welcome to print out and distribute this around your office. Interested in one of ours […]
    Millions of phishing emails will get through automated defenses this year, are your employees ready? An article review. With cybersecurity threats such as cryptocurrency miners and ransomware seeming to dominate the news, it can be easy to forget about older threats such as phishing…but a recent report from cybersecurity firm Tessian reminds us that criminals […]
    The FFIEC’s latest guidance: The Architecture, Infrastructure, and Operations, has brought many changes to exactly how a small financial institution may look at their Technology Planning for 2022. Included in that will be the opportunity to write your first Architecture Plan and we intend to show you what may be involved in that! Have any […]
    While we’re not a news service, we often use current events to comment on trends and our services. This blog is intended to get people thinking about topics and trends in Technology Risk Management, through our article reviews, as well as through original blog articles about current events and our MSSP services (such as our […]
    Following the contribution, Have I Been Pwned will host more than 800 million compromised credentials… An article review. Have any of your login credentials been revealed in a breach?  If you’re unsure about that, Have I Been Pwned (HIBP) can help you out by letting you check against over 600 million compromised credentials…and with the […]
    infotex and Log4j We are keeping our Clients’ safety in mind. To all infotex managed security service Clients: On Friday December 10th, infotex became aware of a zero-day vulnerability in the Apache Log4j library that allows unauthenticated remote code execution. We began incident response and took steps to proactively disable potentially vulnerable applications until we […]
    Another awareness poster for YOUR customers (and users).  Now that we have our own employees aware, maybe it’s time to start posting content for our customers! Download the large versions here: Awareness Poster (Portrait) Awareness Poster (Landscape)   You are welcome to print out and distribute this around your office. Interested in one of ours […]
    Trending: Awareness Posters went “Back to Basics” Here are the top seven posters as of the last twelve months! As always, our Awareness Posters were a hit in 2021! So we decided to run some reports to see what our most popular posters were since November 2020. As everybody loves top ten lists and contests, […]
    Dan is joined by a Panel to discuss the FFIEC’s New AIO Guidance and how it may impact Technology Planning in the future.