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
    Welcome Cybersecurity Conference Attendees! Thanks for joining us for the Cybersecurity Conference today! We have created this page for you to have access to the deliverables from Dan’s talk.  
    What you need to know for compliance coast-to-coast. Back in 2020 we posted an article containing links to data breach laws from each state, and it has proven to be one of our more popular posts.  Because laws surrounding the use (and abuse) of technology are always evolving, we thought it was worth taking another […]
    Why It Rhymes With SEEM (And its Not the I Before E Rule) Another one of those Dan’s New Leaf Posts, meant to inspire thought about IT Governance . . . . It’s the Gestalt. The idea that the whole is greater than the sum of it’s parts. That’s not something that is often brought […]
    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 […]
    Questions about China’s new disclosure laws only highlight the uncertainty about disclosure in general… An article review. China recently made waves in the security world by announcing a new set of data security laws, one of which has added new fuel to a long running debate: how and when should security vulnerabilities be disclosed…and to […]
    Four Conditions … …For Why a Network Can be Anything But a Network! Another one of those Dan’s New Leaf Posts, meant to inspire thought about IT Governance . . . . I have to admit that infotex is being called into engineering meetings with larger organizations these days that are NOT community based banks.  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 […]
    If Zero days need Zero clicks, are there any secure devices in the mix? Tanvee Dhir explores the Pegasus spyware. Another technical post, meant to inspire thought about IT Governance . . . . Introduction Over the past couple of weeks, we have seen multiple stories regarding a powerful piece of spyware called Pegasus sold […]
    Our Lead Non-Technical Auditor takes a look at the new AIO Guidance… Architecture, Infrastructure, and Operations (AIO) is the latest booklet released by the Federal Financial Institutions Examination Council (FFIEC) in their line of  IT Examination Handbooks. It is an update to their 2004 Operations booklet and, as the name implies, expands into the areas […]
    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 […]