Dark Reading is part of the Informa Tech Division of Informa PLC
This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.
How Enterprises Are Assessing Cybersecurity Risk in Today's EnvironmentThe adoption of cloud services spurred by the COVID-19 pandemic has resulted in pressure on cyber-risk professionals to focus on vulnerabilities and new exposures that stem from pandemic-driven changes. Many cybersecurity pros expect fundamental, long-term changes to their organization's computing and data security due to the shift to more remote work and accelerated cloud adoption. Download this report from Dark Reading to learn more about their challenges and concerns.
Incident Readiness and Building Response Playbook
In this special report, learn the Xs and Os of any good security incident readiness and response playbook.
Tweet This
0 Comments
User Rank: Apprentice
11/19/2015 | 6:42:56 PM
As the author notes:
"Any ML system must attempt to separate and differentiate activity based either on pre-defined (i.e. trained learning) or self-learned classifications"
Thus, for a cybersecurity machine learning system to be effective, it must have some principled and structured method to differentiate appropriate and inappropriate access. And, moreover, the system must have the correct context to make such a decision.
The author makes the statement that ML systems struggle to do this:
"Unfortunately, ML systems are not good at describing why a particular activity is anomalous, and how it is related to others. So when the ML system delivers an alert, you still have to do the hard work of understanding whether it is a false positive or not, before trying to understand how the anomaly is related to other activity in the system."
I would point the author to a new line of machine learning algorithms for access auditing called Explanation-Based Auditing.
A detailed peer-reviewed publication can be found at vldb.org/pvldb/vol5/p001_danielfabbri_vldb2012.pdf.
The general idea is to learn why accesses to data occur (e.g., the doctor accessed a record because of an appointment with the patient). This can be modeled as a graph search between the person accessing the data and the data accessed. When such an "explanation" is found, the system can determine the reason for access, filtering it away from manual review.
Thus, as the previous comment states, such as system can remove a tremendous amount of false positives, allowing the privacy or security officer to focus on the unexplained and suspicious.