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
    Today we present a special BONUS awareness poster for YOUR customers (and users).  This update to the April 2022 Awareness Poster takes some cues from the Dan’s New Leaf article: Why Local? Now that we have our own employees aware, maybe it’s time to start posting content for our customers! Check out posters.infotex.com for the […]
    Awareness is 9/11’s of the battle, if we use it! Another one of those Dan’s New Leaf Posts, meant to inspire thought about IT Governance . . . . One of my old college buddies hates banks.  He was turned down for a loan a long time ago and just can’t let go.  I actually […]
    PRESS RELEASE – FOR IMMEDIATE RELEASE SERVICE NEWS Dateline: Dayton, IN, June 22, 2022 We are proud to announce that infotex will now be supporting Endpoint Detection and Response (XDR/MDR)! We can manage/monitor solutions you already have or offer one as part of our service while still maintaining a segregated response posture. In recent years […]
    Over 85 percent of surveyed companies report having no  centralized monitoring of networked industrial devices… An article review. If you are involved in IT within your organization, you’re probably aware of the importance of being able to monitor relevant activity from your networked devices, especially if your organization is involved in healthcare, finance, or government.  […]
    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! Check out posters.infotex.com for the whole collection! Download the large versions here: Awareness Poster (Portrait) Awareness Poster (Landscape)   You are welcome to print out and distribute this around […]
    We always strive to bring you the best content that we possibly can. Your opinion on any content, presentation, service, or anything else you have received from us is important! Please click the button below to let us know how we are doing!  
    What to Expect in an Annual Information Security Report to the Board Webinar-Movie Information security ranks as a top risk to financial institutions, both in terms of likelihood and overall impact. It is important that boards receive annual comprehensive reporting from management about the information security risks and incidents, and the actions taken to address […]
    The Five Precepts of IT Vendor Management Webinar-Movie We’re going back to basics on Vendor Management. This webinar will give you a training tool to help out that new person that is starting to take on the gargantuan task that is Vendor Management.
    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! Check out posters.infotex.com for the whole collection! Download the large versions here: Awareness Poster (Portrait) Awareness Poster (Landscape)   You are welcome to print out and distribute this around […]
    The joint cybersecurity advisory includes the 15 most exploited vulnerabilities reported in 2021… An article review.  While a lot of attention is focused on previously undisclosed or “zero day” attacks, some of the most likely attack vectors are vulnerabilities that have been widely known for weeks or even months.  That’s according to a new joint […]