Companies have AI projects. Security products use AI to keep attackers out and insiders at bay. But what is this "AI" that everyone talks about? In this talk we will explore what artificial intelligence in cyber security is, where the limitations and dangers are, and in what areas we should invest more in AI. We will talk about some of the recent failures of AI in security and invite a conversation about how we verify artificially intelligent systems to understand how much trust we can place in them.
Alongside the AI conversation, we will discover that we need to make a shift in our traditional approach to cyber security. We need to augment our reactive approaches of studying adversary behaviors to understanding behaviors of users and machines to inform a risk-driven approach to security that prevents even zero day attacks.
Artificial Intelligence – Time Bomb or The Promised Land?
1. Raffael Marty
VP Research and Intelligence
Head of X-Labs, Forcepoint
Artificial Intelligence –
Time Bomb or The Promised Land?
Cyber Symposium | September 2019 | Colorado Springs
2. A Brief Summary
We don’t have artificial intelligence (yet)
Algorithms can be dangerous - Understand
your data and your algorithms
We need a paradigm shift in security to escape
the cat and mouse game
Human factors play a key role in detecting and
preventing cyber attacks and insider threat
Build systems that capture “expert knowledge”
and augment human capabilities
5. SECURITY EXAMPLES
Facial Recognition Privacy
Malware Detection Failure
Blacklisting of
Windows Executable
Pentagon AI Fail
Algorithm Bias Data Biases
The Dangers of AI
6. What Makes Algorithms Dangerous?
Algorithms make assumptions about the data.
Algorithms are too easy to use.
Algorithms do not take domain knowledge into account.
History is not a predictor of the future.
7. dest port!
Port 70000?
src ports!
http://vis.pku.edu.cn/people/simingchen/docs/vastchallenge13-mc3.pdfUnderstand Your Data
8. $1 Trillion Has Been Spent Over
The Past 7 Years On Cybersecurity,
With 95% Success …For The Attackers
46% say they can’t prevent attackers
from breaking into internal networks
each time it is attempted.
100% of CIOs believe a breach will
occur through a successful phishing
attack in next 12 months.
Enterprises have seen a 26% increase
in security incidents despite
increasing budgets by 9% YoY.
Source: CyberArk Global Advanced Threat Landscape Report 2018 Sources: Verizon 2018 Data Breach Investigations Report.
9. Escaping the Security Cat and Mouse Game
Reactive
Detection
Threat Intelligence (IOCs)
Event-based
Paradigm Shift
Proactive
Protection and Automation
Behavior of humans and machines
Risk-based
10. Rational for The New Paradigm
Recon Weaponization Delivery Exploitation Installation Execution
• Understand the ‘normal’ behavior of humans and devices
• Try to catch attacker as early as possible,
• Move coverage to later stages
• Does not rely on knowing about types of attacks (zero day resistant)
Behavioral Intelligence
• Constantly changing
• Chasing zero days
• Very reactive
• Focuses on external attackers
Threat Intelligence
Does not work if there is no
‘exploitation’ phase.
E.g., with insiders
Where harm is caused: Critical data and IP
being modified, deleted, or exfiltrated
11. Expanding the Security Framework
1. Understand the
movement of data
Execution
Catch attacks in the
preparation phase
Discover
Explore
Collect
Exfiltrate, Modify, Destroy
Dwell time can be months
2. Understand human
and device behavior:
Monitor human
factors
Monitor for deviations from norm
Recon Weaponize
Assess peer group
membership
89
John
Flag suspicious
entities before
any harm is done
Includes insiders
in the kill chain
12. Understanding Humans and Data
Discover
Explore
Collect
Exfiltrate, Modify, Destroy
Monitor Entities
• Learn their normal behavior
• Learn how they behave relative to their peers
• Learn how they interact with critical data and IP
• Based on deviations, compute an entity risk
Understand Humans
• Track and assess human factors
Shift to a risk-based approach
• An ‘event’ can both be good or bad, depending on
the context of the entity
89
John
13. Addiction, Gambling
Performance
Patterns of
Violations
Interpersonal
Issues
Knowledge,
Skills, Ability
Financial
Distress
Detecting and perceiving risk is
shaped by our ability to integrate
expert knowledge about risk
factors and human behavior.
Accesses
sensitive files
Searches for
sensitive files
Without context, behaviors that
may seem “obviously bad” in
retrospect, may not be noticed.
14. Predisposition
(Vulnerabilities)
Stressors
(Triggering
Factors)
Concerning
Behaviors
A Framework to Understand Humans
• Med/psych conditions
• Personality & Social Skills
• Previous Rule Violations
• Social Network Risks
• Personal (life
changes, health)
• Professional (job
loss, salary, etc.)
• Financial
• Interpersonal
• Policy violations
• Financial
• Mental Health, Addiction
• Social Network, Travel
Note: None of these components alone are indicators of a crime or attack!
RISK
15. Activities
From Activities to Concerning Behaviors
RISK
”Detection Rules” that normally
generate a lot of false positives are not
weighed by the risk of the entities.
Activities that, out of
context would be benign,
now flag an attack
”Risk Adaptive Protection”
Risk adjusted “Detections”
16. Am I here to work
for you, or for
someone else?
Regular
Activities
Activities
Predisposition Stressors
Concerning
Behaviors
• Seeking access or
clearance levels
beyond current need
• Testing security
boundaries
• Multiple usernames & identities
• Social and professional network
• Unreported travel
• Low communication, lack of
social connections in office
• None • Communication
with competitors
17. Research Areas / Where we Need AI
Numerous foundational
problems still unsolved
• Taxonomies
• Entity resolution /
identity attribution
Capturing expert knowledge
• Explicit
• Re-enforcement
• Belief networks
Communication analytics
• NLP
• SNA
• Peer group analytics (CBC)
Risk computation (risk is not linear)
• Belief Networks
Validation and expansion of human
factors framework
18. The Big AI Challenges
Verifyability and Explainability
Privacy
• Doing the right thing for the ‘consumer’
• Compliance with GDPR and other regulations
Efficacy
• How to provably show what algorithms do?
• How to compare against other solutions / algorithms?
• How to know we are protected?
• Preventing ‘snake oil’
Socio-ethical conversation
• Big brother? Surveillance?
Where are the boundaries?
• Where are boundaries of
what is okay to be
collected and analyzed?
Training data for both
supervised algorithms
and hypothesis testing
The world's first dynamic 'non-factor’ based quantum AI encryption software, utilizing multi-dimensional encryption technology, including time,
music's infinite variability, artificial intelligence, and most notably mathematical constancies to generate entangled key pairs. – Snake Oil
19. Takeaways
“The way algorithms are used is
often dangerous. Hire experts.”
“We need a paradigm shift to escape
the security cat and mouse game.”
“Understanding human factors can
help getting ahead of attackers”