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 Machine Learning, AI & Deep Learning Improve CybersecurityMachine intelligence is influencing all aspects of cybersecurity. Organizations are implementing AI-based security to analyze event data using ML models that identify attack patterns and increase automation. Before security teams can take advantage of AI and ML tools, they need to know what is possible. This report covers:
-How to assess the vendor's AI/ML claims
-Defining success criteria for AI/ML implementations
-Challenges when implementing AI
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
1 Comments
User Rank: Apprentice
9/20/2016 | 8:57:32 PM
I see two problems at play here:
CISOs don't know how to measure the return on investment existing security controls are providing, hence they are not able to articulate the value
CISOs are likely not getting the best value out of some investments - not utilising all of the features; purchase was made on a whim raher than rooted in solid discussiosn around risk; etc.
To actually make a difference in the cybersecurity industry, perhaps CISOs should try changing the way they think about the problem:
Move beyond the notion of security and even regulatory compliance (PCI-DSS is good but limited). Even ISO 27001, NIST and other frmaeworks have their flaws. Also forget about the kill chain. It describes only a subset of today's attacks.
Start thinking along these lines. Every devastating impact, be it operational, physical, personal, legal, reputational, financial, or a combination of these we suffer because of cyber crime happens because:
We failed to identify and remediate vulnerabilities in our critical assets;
We failed to predict and prevent threats that took exploited those vulnerabilities;
We failed to detect and respond to the attack that manifested from a threat;
We failed to confirm and recover from a breach in a timely and coordinated fashion.
Translate this into the requirement for a shift in mindset and culture from security or compliance to a healthy dose of:
1. asset management (asset identification and classification)
2. vulnerability management (vulnerability identification and remediation)
3. threat management (threat prediction and prevention)
4. incident management (attack detection and response)
5. continuity management (breach confirmation and recovery)
6. crisis management (impact reduction, acceptance, avoidance and transfer)
I call this "cyber resilience" and, yes, it actually works to reduce the rate and cost of cybercrime.