Blog
/
AI
/
June 12, 2023

How Darktrace AI Protects 8,400 Customers

This blog describes how Darktrace DETECT and RESPOND can help organizations reduce privacy and security risks related to generative AI.
Inside the SOC
Darktrace cyber analysts are world-class experts in threat intelligence, threat hunting and incident response, and provide 24/7 SOC support to thousands of Darktrace customers around the globe. Inside the SOC is exclusively authored by these experts, providing analysis of cyber incidents and threat trends, based on real-world experience in the field.
Written by
Jack Stockdale OBE FREng
Chief Technology Officer
Default blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog image
12
Jun 2023

Generative AI and Large Language Model (LLM) tools have entered the mainstream of public consciousness this year, with people using the likes of OpenAI’s ChatGPT and Google Bard for everything from helping web searches to using the AI capabilities to drive efficiency in the workplace.

At Darktrace, we have long understood the potential for AI to be one of the most transformative technological opportunities of our time. Our Darktrace Cyber AI Research Centre in Cambridge has been researching and developing AI tools for over a decade – tools like Darktrace DETECT™ and RESPOND™ which use a variety of AI technology to keep 8,400 customers around the world safe from cyber disruption. 

As pioneers of AI and understanding its potential to change the world, we recognize that in 2023, the AI genie is out of the bottle. AI tools are rapidly becoming part of our day to day lives. 

74% of active customer deployments have employees using generative AI tools in the workplace [1]

While generative AI tools have the power to increase productivity and augment human creativity, businesses need to move quickly to keep up with the pace of innovation. These tools carry potential privacy and security risks if used incorrectly or without proper policies in place that match the unique needs of the business – creating challenges for CISOs.

Privacy and Security Risks with Generative AI 

Government agencies like the UK’s National Cyber Security Centre (NCSC) have already issued guidance about the need to manage risk when using generative AI tools and other LLMs in the workplace. In the United States, the Cybersecurity and Infrastructure Agency (CISA) has also expressed concerns about the security implications of generative AI.

One of the reasons for this is because LLMs can learn from your prompts, storing information entered and using it to train datasets. With that data in the system, it is possible that if someone enters the right prompt, the LLM could potentially use your company’s data in response to a query.

And if the information you entered contains sensitive files or data such as intellectual property or know-how, financial reports, confidential internal documents, or sales numbers, it could become part of the third-party AI model and potentially available to others, creating privacy, intellectual property, and security risks if the appropriate guardrails are not in place. 

How Darktrace Helps Manage Generative AI Use 

In response to the growing use of generative AI tools, Darktrace has announced new risk and compliance models to help Darktrace customers address concerns around the risk of IP loss and data leakage.

We’re excited about how immensely powerful these generative AI tools are, with the capability to help people and businesses work efficiently– but like any other technology, there’s the risk that they could be inadvertently misused if not managed or monitored correctly. That’s why the new risk and compliance models for Darktrace DETECT™ and RESPOND™ make it easier for customers to put guardrails in place to monitor, and when necessary, respond to activity and connections to generative AI and LLM tools such as AutoGPT, ChatGPT, Stable Diffusion, Claude, and more. 

Each business will have its own distinct policies and needs related to generative AI tools, so we’ve also made it easier for customers to add their own list of tools to monitor for. 

Darktrace’s Self-Learning AI makes it possible to detect generative AI activity that may deviate from company policies or best practices. We bring our AI to each customer’s data, and it learns the day-to-day workings of every user, asset, and device – building an understanding of your business’s unique ‘pattern of life’.  That’s why it can detect even subtle anomalies that could indicate a threat to your business and autonomously respond, containing the threat in seconds.  

In May 2023, Darktrace Self-Learning AI detected and prevented an upload of over 1GB of data to a generative AI tool at one of its customers. [2]

With these guardrails in place, Darktrace customers can take advantage of the opportunity using generative AI and LLMs provide, while remaining protected against the potential security, IP, and privacy risks.

Using AI Safely and Responsibly

At Darktrace, we believe that recent advances in generative AI and LLMs are an important addition to the growing arsenal of AI techniques that will transform cyber security. After all, we have been utilizing AI, including LLMs and generative AI, across all of our products for years – including in Cyber AI Analyst for real time analysis of incidents, helping Darktrace customers use the power of AI to stay protected from cyber threats.

But we also believe in the responsible development and deployment of different AI techniques, which is why we are providing the tools customers need to use AI safely and responsibly. 

Our Self-Learning AI is already helping more than 8,400 businesses fight back and protect themselves against cyber threats and disruptions for the past ten years – with these new tools, CISOs can ensure that productivity is boosted by generative AI, without needing to worry about the potential security risks. Our AI learns the business in real time, all the time. It’s a Self-Learning AI. And the impact we’ve seen on improved security outcomes has been enormous.

Self-Learning AI informs Darktrace’s Cyber AI Loop, an interconnected, comprehensive set of dynamically related capabilities working together autonomously to create a continuous feedback loop to prevent, detect, respond, and heal from cyber-attacks. Ensuring that data, people, and businesses stay protected from cyber threats.

Figure 1: Darktrace Cyber AI Loop

References

[1] Based on data obtained on June 2nd, 2023, from active customer deployments with Call Home enabled, where Darktrace detected generative AI activity at some point.

[2]  Based on data obtained on June 2nd, 2023, from active customer deployments with Call Home enabled, where Darktrace detected generative AI activity at some point.

Inside the SOC
Darktrace cyber analysts are world-class experts in threat intelligence, threat hunting and incident response, and provide 24/7 SOC support to thousands of Darktrace customers around the globe. Inside the SOC is exclusively authored by these experts, providing analysis of cyber incidents and threat trends, based on real-world experience in the field.
Written by
Jack Stockdale OBE FREng
Chief Technology Officer

More in this series

No items found.

Blog

/

/

April 21, 2025

Why Asset Visibility and Signature-Based Threat Detection Fall Short in ICS Security

operational technology operators looking at equipment Default blog imageDefault blog image

In the realm of Industrial Control System (ICS) security, two concepts often dominate discussions:

  1. Asset visibility
  2. Signature-based threat detection

While these are undoubtedly important components of a cybersecurity strategy, many organizations focus on them as the primary means to enhance ICS security. However, this is more of a short-term approach and these organizations often realize too late that these efforts do not translate into actually securing their environment.

To truly secure your environment, organizations should focus their efforts on anomaly detection across core network segments. This shift enables enhanced threat detection, while also providing a more meaningful and dynamic view of asset communication.

By prioritizing anomaly detection, organizations can build a more resilient security posture, detecting and mitigating threats before they escalate into serious incidents.

The shortcomings of asset visibility and signature-based threat detection

Asset visibility is frequently touted as the foundation of ICS security. The idea is that you cannot protect what you cannot see.

However, organizations that invest heavily in asset discovery tools often end up with extensive inventories of connected devices but little actionable insight into their security posture or risk level, let alone any indication as to whether these assets have been compromised.

Simply knowing what assets exist does not equate to securing them.

Worse, asset discovery is often a time-consuming static process. By the time practitioners complete their inventory, not only is there likely to have been changes to their assets, but the threat landscape may have already evolved, introducing new vulnerabilities and attack vectors  that were not previously accounted for.

Signature-based detection is reactive, not proactive

Traditional signature-based threat detection relies on known attack patterns and predefined signatures to identify malicious activity. This approach is fundamentally reactive because it can only detect threats that have already been identified elsewhere.

In an ICS environment where cyber-attacks on OT systems have become more frequent, sophisticated, and destructive, signature-based detection provides a false sense of security while failing to detect sophisticated, previously unseen threats:

Additionally, adversaries often dwell within OT networks for extended periods, studying their specific conditions to identify the most effective way to cause disruption. This means that the likelihood of any attack within OT network looking the same as a previous attack is unlikely.

Implementation effort vs. actual security gains

Many organizations spend considerable time and resources implementing asset visibility solutions and signature-based detection systems only to be required to constantly tune and adjust the sensitivity of the solution.

Despite these efforts, these tools often fail to deliver the level of protection expected, leaving gaps in detection, an overwhelming amount of asset data, and a constant stream of false positives and false negatives from signature-based systems.

A more effective approach: Anomaly detection at core network segments

While it's important to understand the type of device involved during alert triage, organizations should shift their focus from static asset visibility and threat signatures to anomaly detection across critical network segments. This method provides a superior approach to ICS security for several reasons:

Proactive threat detection

Anomaly detection monitors network behavior in real time and identifies deviations . This means that even novel or previously unseen threats can be detected based on unusual network activity, rather than relying on predefined signatures.

Granular security insights

By analyzing traffic patterns across key network segments, organizations can gain deeper insights into how assets interact. This not only improves threat detection but also organically enhances asset visibility. Instead of simply cataloging devices, organizations gain meaningful visibility into how they behave within the network, understanding their unique pattern of life, and making it easier to detect malicious activity.

Efficiency and scalability

Implementing anomaly detection allows security teams to focus on real threats rather than sifting through massive inventories of assets or managing signature updates. It scales better with evolving threats and provides continuous monitoring without requiring constant manual intervention.

Enhanced threat detection for critical infrastructure

Unlike traditional security approaches that rely on static baselines or threat intelligence that doesn't reflect the unique behaviors of your OT environment, Darktrace / OT uses multiple AI techniques to continuously learn and adapt to your organization’s real-world activity across IT, OT, and IoT.

By building a dynamic understanding of each device’s pattern of life, it detects threats at every stage of the kill chain — from known malware to zero-days and insider attacks — without overwhelming your team with false positives or unnecessary alerts. This ensures scalable protection as your environment evolves, without a significant increase in operational overhead.

[related-resource]

Continue reading
About the author
Jeffrey Macre
Industrial Security Solutions Architect

Blog

/

/

April 16, 2025

Introducing Version 2 of Darktrace’s Embedding Model for Investigation of Security Threats (DEMIST-2)

woman looking at laptop at deskDefault blog imageDefault blog image

DEMIST-2 is Darktrace’s latest embedding model, built to interpret and classify security data with precision. It performs highly specialized tasks and can be deployed in any environment. Unlike generative language models, DEMIST-2 focuses on providing reliable, high-accuracy detections for critical security use cases.

DEMIST-2 Core Capabilities:  

  • Enhances Cyber AI Analyst’s ability to triage and reason about security incidents by providing expert representation and classification of security data, and as a part of our broader multi-layered AI system
  • Classifies and interprets security data, in contrast to language models that generate unpredictable open-ended text responses  
  • Incorporates new innovations in language model development and architecture, optimized specifically for cybersecurity applications
  • Deployable across cloud, on-prem, and edge environments, DEMIST-2 delivers low-latency, high-accuracy results wherever it runs. It enables inference anywhere.

Cybersecurity is constantly evolving, but the need to build precise and reliable detections remains constant in the face of new and emerging threats. Darktrace’s Embedding Model for Investigation of Security Threats (DEMIST-2) addresses these critical needs and is designed to create stable, high-fidelity representations of security data while also serving as a powerful classifier. For security teams, this means faster, more accurate threat detection with reduced manual investigation. DEMIST-2's efficiency also reduces the need to invest in massive computational resources, enabling effective protection at scale without added complexity.  

As an embedding language model, DEMIST-2 classifies and creates meaning out of complex security data. This equips our Self-Learning AI with the insights to compare, correlate, and reason with consistency and precision. Classifications and embeddings power core capabilities across our products where accuracy is not optional, as a part of our multi-layered approach to AI architecture.

Perhaps most importantly, DEMIST-2 features a compact architecture that delivers analyst-level insights while meeting diverse deployment needs across cloud, on-prem, and edge environments. Trained on a mixture of general and domain-specific data and designed to support task specialization, DEMIST-2 provides privacy-preserving inference anywhere, while outperforming larger general-purpose models in key cybersecurity tasks.

This proprietary language model reflects Darktrace's ongoing commitment to continually innovate our AI solutions to meet the unique challenges of the security industry. We approach AI differently, integrating diverse insights to solve complex cybersecurity problems. DEMIST-2 shows that a refined, optimized, domain-specific language model can deliver outsized results in an efficient package. We are redefining possibilities for cybersecurity, but our methods transfer readily to other domains. We are eager to share our findings to accelerate innovation in the field.  

The evolution of DEMIST-2

Key concepts:  

  • Tokens: The smallest units processed by language models. Text is split into fragments based on frequency patterns allowing models to handle unfamiliar words efficiently
  • Low-Rank Adaptors (LoRA): Small, trainable components added to a model that allow it to specialize in new tasks without retraining the full system. These components learn task-specific behavior while the original foundation model remains unchanged. This approach enables multiple specializations to coexist, and work simultaneously, without drastically increasing processing and memory requirements.

Darktrace began using large language models in our products in 2022. DEMIST-2 reflects significant advancements in our continuous experimentation and adoption of innovations in the field to address the unique needs of the security industry.  

It is important to note that Darktrace uses a range of language models throughout its products, but each one is chosen for the task at hand. Many others in the artificial intelligence (AI) industry are focused on broad application of large language models (LLMs) for open-ended text generation tasks. Our research shows that using LLMs for classification and embedding offers better, more reliable, results for core security use cases. We’ve found that using LLMs for open-ended outputs can introduce uncertainty through inaccurate and unreliable responses, which is detrimental for environments where precision matters. Generative AI should not be applied to use cases, such as investigation and threat detection, where the results can deeply matter. Thoughtful application of generative AI capabilities, such as drafting decoy phishing emails or crafting non-consequential summaries are helpful but still require careful oversight.

Data is perhaps the most important factor for building language models. The data used to train DEMIST-2 balanced the need for general language understanding with security expertise. We used both publicly available and proprietary datasets.  Our proprietary dataset included privacy-preserving data such as URIs observed in customer alerts, anonymized at source to remove PII and gathered via the Call Home and aianalyst.darktrace.com services. For additional details, read our Technical Paper.  

DEMIST-2 is our way of addressing the unique challenges posed by security data. It recognizes that security data follows its own patterns that are distinct from natural language. For example, hostnames, HTTP headers, and certificate fields often appear in predictable ways, but not necessarily in a way that mirrors natural language. General-purpose LLMs tend to break down when used in these types of highly specialized domains. They struggle to interpret structure and context, fragmenting important patterns during tokenization in ways that can have a negative impact on performance.  

DEMIST-2 was built to understand the language and structure of security data using a custom tokenizer built around a security-specific vocabulary of over 16,000 words. This tokenizer allows the model to process inputs more accurately like encoded payloads, file paths, subdomain chains, and command-line arguments. These types of data are often misinterpreted by general-purpose models.  

When the tokenizer encounters unfamiliar or irregular input, it breaks the data into smaller pieces so it can still be processed. The ability to fall back to individual bytes is critical in cybersecurity contexts where novel or obfuscated content is common. This approach combines precision with flexibility, supporting specialized understanding with resilience in the face of unpredictable data.  

Along with our custom tokenizer, we made changes to support task specialization without increasing model size. To do this, DEMIST-2 uses LoRA . LoRA is a technique that integrates lightweight components with the base model to allow it to perform specific tasks while keeping memory requirements low. By using LoRA, our proprietary representation of security knowledge can be shared and reused as a starting point for more highly specialized models, for example, it takes a different type of specialization to understand hostnames versus to understand sensitive filenames. DEMIST-2 dynamically adapts to these needs and performs them with purpose.  

The result is that DEMIST-2 is like having a room of specialists working on difficult problems together, while sharing a basic core set of knowledge that does not need to be repeated or reintroduced to every situation. Sharing a consistent base model also improves its maintainability and allows efficient deployment across diverse environments without compromising speed or accuracy.  

Tokenization and task specialization represent only a portion of the updates we have made to our embedding model. In conjunction with the changes described above, DEMIST-2 integrates several updated modeling techniques that reduce latency and improve detections. To learn more about these details, our training data and methods, and a full write-up of our results, please read our scientific whitepaper.

DEMIST-2 in action

In this section, we highlight DEMIST-2's embeddings and performance. First, we show a visualization of how DEMIST-2 classifies and interprets hostnames, and second, we present its performance in a hostname classification task in comparison to other language models.  

Embeddings can often feel abstract, so let’s make them real. Figure 1 below is a 2D visualization of how DEMIST-2 classifies and understands hostnames. In reality, these hostnames exist across many more dimensions, capturing details like their relationships with other hostnames, usage patterns, and contextual data. The colors and positions in the diagram represent a simplified view of how DEMIST-2 organizes and interprets these hostnames, providing insights into their meaning and connections. Just like an experienced human analyst can quickly identify and group hostnames based on patterns and context, DEMIST-2 does the same at scale.  

DEMIST-2 visualization of hostname relationships from a large web dataset.
Figure 1: DEMIST-2 visualization of hostname relationships from a large web dataset.

Next, let’s zoom in on two distinct clusters that DEMIST-2 recognizes. One cluster represents small businesses (Figure 2) and the other, Russian and Polish sites with similar numerical formats (Figure 3). These clusters demonstrate how DEMIST-2 can identify specific groupings based on real-world attributes such as regional patterns in website structures, common formats used by small businesses, and other properties such as its understanding of how websites relate to each other on the internet.

Cluster of small businesses
Figure 2: Cluster of small businesses
Figure 3: Cluster of Russian and Polish sites with a similar numerical format

The previous figures provided a view of how DEMIST-2 works. Figure 4 highlights DEMIST-2’s performance in a security-related classification task. The chart shows how DEMIST-2, with just 95 million parameters, achieves nearly 94% accuracy—making it the highest-performing model in the chart, despite being the smallest. In comparison, the larger model with 2.78 billion parameters achieves only about 89% accuracy, showing that size doesn’t always mean better performance. Small models don’t mean poor performance. For many security-related tasks, DEMIST-2 outperforms much larger models.

Hostname classification task performance comparison against comparable open source foundation models
Figure 4: Hostname classification task performance comparison against comparable open source foundation models

With these examples of DEMIST-2 in action, we’ve shown how it excels in embedding and classifying security data while delivering high performance on specialized security tasks.  

The DEMIST-2 advantage

DEMIST-2 was built for precision and reliability. Our primary goal was to create a high-performance model capable of tackling complex cybersecurity tasks. Optimizing for efficiency and scalability came second, but it is a natural outcome of our commitment to building a strong, effective solution that is available to security teams working across diverse environments. It is an enormous benefit that DEMIST-2 is orders of magnitude smaller than many general-purpose models. However, and much more importantly, it significantly outperforms models in its capabilities and accuracy on security tasks.  

Finding a product that fits into an environment’s unique constraints used to mean that some teams had to settle for less powerful or less performant products. With DEMIST-2, data can remain local to the environment, is entirely separate from the data of other customers, and can even operate in environments without network connectivity. The size of our model allows for flexible deployment options while at the same time providing measurable performance advantages for security-related tasks.  

As security threats continue to evolve, we believe that purpose-built AI systems like DEMIST-2 will be essential tools for defenders, combining the power of modern language modeling with the specificity and reliability that builds trust and partnership between security practitioners and AI systems.

Conclusion

DEMIST-2 has additional architectural and deployment updates that improve performance and stability. These innovations contribute to our ability to minimize model size and memory constraints and reflect our dedication to meeting the data handling and privacy needs of security environments. In addition, these choices reflect our dedication to responsible AI practices.

DEMIST-2 is available in Darktrace 6.3, along with a new DIGEST model that uses GNNs and RNNs to score and prioritize threats with expert-level precision.

[related-resource]

Continue reading
About the author
Margaret Cunningham, PhD
Director, Security & AI Strategy, Field CISO
Your data. Our AI.
Elevate your network security with Darktrace AI