Artificial Intelligence · cybersecurity

Artificial Intelligence (AI) Cybersecurity: It’s All About Behavior!

The latest leading-edge data intelligence topics referred to as Artificial Intelligence (AI), Machine Learning (ML) and, Artificial Neural Networks (ANN) are currently experiencing significant venture and corporate capital investments. Some of the advantages of ingesting large quantities of data and creating a corpus of knowledge to draw insights are very interesting for complex subjects such as cybersecurity, healthcare and financial services. The use cases of AI in healthcare such as DNA/genome research are truly captivating to read. The parallels to cybersecurity research and respective knowledge base for predicting and analyzing data will be step-functions of change needed to understand the data collection and interpretation of threats. The application of any form of AI includes a “people factor,” as directly linked to both ends of a “cyber activity.” A “cyber event” is started by a person and the resolution is implemented and managed by the same.

The behavior part of cybersecurity also involves people, but machine behavior plays a significant role in cyber events. For example, if we can measure a baseline of machine behavior that is “known good,” then we can react—potentially in real-time—to machine changes in behavior. There are many parameters to consider and behaviors that may be considered non-issues to filter; however, having a system of behavioral analytics under the category of AI/ML/ANN brings data-driven decision making.

A few scenarios to outline this include known devices on the network or IoT devices changing their state. In the first case of known devices, this has been a topic we have been discussing in the security space for a very long time. Products and technologies have been built for attestation, key management and device authentication—to capture a few categories. As we move up a level from the cryptography space to understanding the metadata a device produces, we can measure changes, arrival, departure and state. By observing anything with an IP address in relationship to the context of its metadata, we can filter “good” and “bad” activities, behaviors and changes. If a known device comes on the network at 8 am on Monday normally, but an unknown device comes on the network at 3:00 am, we can create an action to change that behavior and thus become proactive in our cyber preparedness. Alternately, if a known device that was once considered “good” starts talking to a “bad” actor site or shows a change in its metadata that is considered out of policy/standard, then actions can be taken to quarantine or remediate accordingly.

In the second example of IoT devices changing their state, we have seen this with IP cameras, and medical devices. The potential case of industrial systems being taken over by the “zombie robot apocalypse” is not as far removed from reality as one might think. Hackers can exploit flaws and create subtle changes to industrial control systems, which could be dramatic in scale or event. I am not suggesting that the machines will take over the world, but I am suggesting close monitoring of IoT devices for behavioral changes that could indicate the presence or possibility of a wider scale issue.

As an industry, we can start to move from a reactive to a proactive state in the category of cyber preparedness. A real-time approach to monitoring device behaviors could reduce cyber event time to discovery from the current industry average of 256 days. The cost of discovery time is escalating every year. Our small and-medium businesses cannot afford the costs of remediation and losses that accompany a cyber event. The statistics of survival for SMBs in a cyber event estimate that roughly 60 percent or 6 out 10 will not be in business in six months.

The current state of cybersecurity necessitates the establishment of continuous monitoring practices—to monitor both known devices on networks and IoT devices changing their state. The innovations of artificial intelligence (AI), machine learning (ML) and artificial neural networks (ANN) are paving the way for a proactive cyber approach.

 

cybersecurity

Where are cybersecurity threats coming from?

There has been a lot of recent news and discussion about several malware variants that have been defined as ransomware attacks. There are and have been other damaging malware attacks, but ransomware popularity is currently very well publicized.

Ransomware attacks are not simple but are commonplace in the market today. These attacks typically find their way into an organization through social engineering. To be more specific, the malware is embedded in an attachment as an executable. There are several outcomes from ransomware that we have seen thus far: an individual machine is encrypted and the decryption key is held for ransom by the attacker and a currency request of a “Bitcoin” is requested to decrypt the machine in question. The nastier variants can traverse from machine to machine through the network, creating a systemwide infection. This attack causes severe networkwide shutdowns, causing an organization to recover through more significant ransom payments, or if the company was prepared, backup remediation steps are taken.

The availability of targets for ransomware attacks is almost unlimited, with small and medium businesses (SMBs) being the most vulnerable. Most SMBs are not well-equipped to handle these attacks. There are a few typical dilemmas the SMBs face: What is a bitcoin and how do I get one/them? We did not prepare our network and back-up processes to remediate the problem. Lastly, law enforcement does not recommend payment to the ransom and there is no guarantee that the attacker will actual provide a legitimate decryption key.

The other type of attack—less publicized but equally damaging—is the “insider threat,” wherein the attacker is currently or was previously authorized to work inside your organization. These individuals can cause incalculable damage to your company. As an example, these can be system level attacks or result in losses of intellectual property. The insider threat is as complex to detect and remediate as an external attack. The differentiator here is the insider knows the weaknesses and knows where to find the most valuable information. As with external threats, experts recommend both employee training and monitoring capabilities to detect real-time behavioral changes.

Some additional processes to help SMBs monitor their employees, networks and behaviors to identify insider and external threats include:

  • Developing and enforcing policies for access to information systems
  • Monitoring and auditing inappropriate access – remediating upon discovery
  • Enforcing authentication and limited login attempt processes
  • Monitoring printers, downloading (large), queries and email
  • Deploying real-time networks monitoring for flow, files, connections, ports and suspicious IPs
  • Managing identities of current and past employees

 

 

cybersecurity

The background on Industry Cybersecurity Standards – NIST, CSET, DFARS

How to best understand the  Cybersecurity guidance and volumes of information is an ominous challenge? The foundational cybersecurity work produced by NIST (National Institute for Standards and Technology) is  a comprehensive cybersecurity review. Rather than diving too deep in to NIST and the regulatory nature of the definition of classified vs unclassified information and its protection, I will touch on the value of measuring a commercial organizations cybersecurity posture.
The recommended NIST standards, should you be interested to read, are noted as NIST SP 800-171 http://csrc.nist.gov/publications/drafts/800-171/sp800_171_draft.pdf, published October 18, 2015 identifies a couple very useful tools and premises for measurements. One tool, that is very useful is the CSET (Cyber Security Evaluation Tool) https://cset.inl.gov/SitePages/Home.aspx, which is a self-test, that any organization can use for “free.” While this tool is comprehensive in nature, it does require the user of the tool, to have an in-depth IT and Cyber background to accurately answer the 109 technical questions.
The second very useful part of the NIST publication is the breakdown of measurements into the specific 14-controls: Access Control, Awareness and Training, Auditing and Accountability, Configuration Management, Identification and Authentication, Incident Response, Maintenance, Media Protection, Personnel Security, Physical Protection, Risk Assessment, Security Assessment, System and Communication Protection, System and Information Integrity. By accurately measuring these controls in both a self-test environment (CSET) and using network scanning/situational awareness tools, an organization can get a true grade of their cybersecurity posture to uncover looming vulnerabilities.
The tool (CSET) produces a private result that are defined as a percentage out of 100%, with 100% being equal to compliance. The commercial customer can be measured against a publicly available industry standard, that has been architected to look at a company’s posture without bias. The meaning is to use an industry standard, and by definition, an industry standard is not proprietary. The consulting, technology and solutions market typically use a proprietary methodology to assist in assessments. However, leveraging the standards will give your organization a measurable outcome and baseline for improvements.
Now that we have reviewed the foundations, putting this into practice and having a vision of the effect on your company is an important discussion. Today, any organization, that supplies the federal government with product, solutions or services under a DOD contract, MUST BE COMPLIANT BY 12/31/2017. This date is non-negotiable. Organizations can self-assess or outsource the entire process to cyber experts. There are a few other requirements for compliance beyond providing the 100% System Security Plan, which include a Plan of Action and Milestones (your cyber improvement plan), a gap analysis (what are my company challenges), continuous monitoring and cyber incident reporting processes. The commercial market cyber need is increasing daily, with both compliance, business continuity needs and basic preparedness.  The standards approach is a very good methodology and starting place.
Other industries that will see changes for compliance in variations of this standard include: Healthcare, Financial Services, Food Safety, manufacturing and the Small and Medium Businesses (SMB’s). Here are some great references to see where the future of Cybersecurity preparedness is heading.

  • DFARS 252.204-7012 referenced as contract language for federal NIST 800-171 – designed for non-federal information systems (commercial)
  • NIST 800-53 cybersecurity framework for Federal information systems
  • Cybersecurity Framework for critical infrastructure – references NIST 800-53
  • Health Care Industry Cybersecurity Task Force recommends NIST Cybersecurity framework
cybersecurity · Malware · Ransomeware

Malware & Ransomware: SMB Best Practices

petya1-768x426[1]

In the wake of the past several weeks of broad and damaging cyber-attacks, it’s important that we talk about proactive measures the small and medium organizations should consider to protect your environment. Many of my colleagues have articulated the damage and origins of the recent attacks: WannaCry & Petya. I find these insights extremely valuable to understand the root and attributions of the malware itself. These publicized reports provide all sized organizations context to the magnitude of the current and future damages these organized type attacks can deliver.
The small and medium business sector has the largest threat landscape for cyber-attacks. The potential damages to the hundreds of thousands of businesses in the USA is an alarming statistic. The questions that consistently are asked by the small and medium business is; what should I do to protect my company? And, how can I afford the equipment, software and human resources required to truly become cyber prepared? Good news! There are options and practical real-world solutions available.
Many smaller organizations don’t have the internal resources to research both the industry standards and proprietary models to understand what is the best cybersecurity approach. A best practice is to use a methodical standards-based approach to build cyber awareness, develop a plan to improve and implement a proactive monitoring solution as an appropriate start to cyber preparedness. Noted below are strategic and tactical plans the small and medium businesses should implement immediately.

Strategic recommendations:

  • Cybersecurity assessment – understand your current posture to identify vulnerabilities
  • Gap analysis – a comprehensive view of what needs improvement
  • Plan of Action – a detailed, real-world and affordable improvement plan
  • Continuous monitoring – become a proactive cyber aware company to know when changes occur

Tactical recommendations for WannaCry & Petya variants:

  • Ensure systems are patched and all antivirus programs are up to date
  • Implement and determine if backup systems are effectively configured
  • Restore only backups that have been securely managed
  • Isolate any unpatched systems
  • Monitor all networks and device connectivity
cybersecurity · IoT · Malware · Ransomeware

“Flipper” role in protection of our resources – it’s an IoT fish story!

Many may remember the TV series, “Flipper.” For those who do not remember, the theme and plot is as follows: Flipper, a bottle-nose dolphin, helps to protect his lagoon park and preserve its wild inhabitants. He is instrumental in apprehending criminals and thugs in the park.

How does this story draw parallels to cybersecurity?

This past week, an unnamed North American casino experienced a cybersecurity breach via a fish tank. The casino’s self-cleaning fish tank, programmed via sensors to monitor water temperatures and fish feeding schedules, was targeted by hackers. Through the fish tank system, the cyber thugs broke into the casino’s computer network and downloaded sensitive data to a Finland location.

Connecting the dots of this story back to “Flipper,” the idea of observing and monitoring one’s environment is vitally important. Like Flipper—whose role was to apprehend criminals through observation and data collection—we must remain vigilant, and can no longer blindly trust even the most innocent of devices, such as programmed fish tanks.

Fish tanks are now IoT devices on our networks and, as seen in the case of this casino, can create an open door for clever cyber thugs. Today’s cyber thugs and criminals leave breadcrumbs of information that we can collect to understand the risks associated with certain IT decisions. The same advice and best practices apply to fish tanks as they do to any other sensor on our networks. Understand, Monitor, Prevent and Segment to protect your most critical assets: DATA!

http://money.cnn.com/2017/07/19/technology/fish-tank-hack-darktrace/index.html