November 3, 2023 at 09:42AM
Artificial intelligence (AI) in cybersecurity is increasingly important as the threat landscape evolves. BlackBerry is a leader in this space, using predictive AI tools to block new malware attacks. Their model demonstrates a strong temporal predictive advantage, with protection continuing for up to 18 months without a model update. BlackBerry Cylance AI offers outstanding performance and speed in detecting and preventing malware.
In this meeting, the main topic discussed is the importance of outcomes when it comes to artificial intelligence (AI) in cybersecurity. It is mentioned that as the threat landscape evolves and generative AI becomes more prevalent among both defenders and attackers, it becomes increasingly important and difficult to evaluate the effectiveness of AI-based security offerings.
The meeting notes suggest asking the right questions to identify solutions that deliver value and return on investment (ROI) rather than marketing hype. Some examples of these questions are: “Can your predictive AI tools sufficiently block what’s new?” and “What actually signals success in a cybersecurity platform powered by artificial intelligence?”
The notes highlight BlackBerry as a leader in AI and machine learning (ML) in the cybersecurity space. BlackBerry’s AI and ML patent portfolio demonstrate their expertise and well-informed perspective on what works in this field.
The evolution of AI in cybersecurity is discussed, with reference to CylancePROTECT EPP being one of the earliest examples of ML and AI in cybersecurity. Given the increasing threat of new malware attacks, the development of predictive tools is crucial. BlackBerry’s data science and machine learning teams are dedicated to enhancing the performance of their predictive AI tools. Third-party tests have confirmed that Cylance ENDPOINT successfully blocks 98.9% of threats, even new variants.
The temporal aspect of ML models in cybersecurity is emphasized. The ability of ML models to detect and respond to threats in real-time, particularly in malware pre-execution protection, is crucial. Temporal resilience, which measures a model’s performance against both past and future attacks, is highlighted as essential for threat detection. BlackBerry Cylance’s model has demonstrated a strong temporal predictive advantage, maintaining high detection rates over time without frequent model updates.
The meeting notes mention the novelty of BlackBerry Cylance’s ML model inference technology, which can infer whether something is a threat even if it has never been seen before. This unique hybrid method of distributed inference sets BlackBerry apart. The latest model represents the pinnacle of innovation and improvements in this technology.
The meeting concludes by emphasizing the maturity and effectiveness of BlackBerry Cylance AI. With a multi-year predictive advantage, it has protected businesses and governments globally from cyberattacks. The outcomes of using Cylance AI show that not all AI is created equal. The notes also provide a link to a detailed research article by BlackBerry for further reading on predictive AI.
Is there anything specific you would like assistance with regarding these meeting notes?