Blog
/

Inside the SOC

/
October 30, 2023

Exploring AI Threats: Package Hallucination Attacks

Default blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog imageDefault blog image
30
Oct 2023
Learn how malicious actors exploit errors in generative AI tools to launch packet attacks. Read how Darktrace products detect and prevent these threats!

AI tools open doors for threat actors

On November 30, 2022, the free conversational language generation model ChatGPT was launched by OpenAI, an artificial intelligence (AI) research and development company. The launch of ChatGPT was the culmination of development ongoing since 2018 and represented the latest innovation in the ongoing generative AI boom and made the use of generative AI tools accessible to the general population for the first time.

ChatGPT is estimated to currently have at least 100 million users, and in August 2023 the site reached 1.43 billion visits [1]. Darktrace data indicated that, as of March 2023, 74% of active customer environments have employees using generative AI tools in the workplace [2].

However, with new tools come new opportunities for threat actors to exploit and use them maliciously, expanding their arsenal.

Much consideration has been given to mitigating the impacts of the increased linguistic complexity in social engineering and phishing attacks resulting from generative AI tool use, with Darktrace observing a 135% increase in ‘novel social engineering attacks’ across thousands of active Darktrace/Email™ customers from January to February 2023, corresponding with the widespread adoption of ChatGPT and its peers [3].

Less overall consideration, however, has been given to impacts stemming from errors intrinsic to generative AI tools. One of these errors is AI hallucinations.

What is an AI hallucination?

AI “hallucination” is a term which refers to the predictive elements of generative AI and LLMs’ AI model gives an unexpected or factually incorrect response which does not align with its machine learning training data [4]. This differs from regular and intended behavior for an AI model, which should provide a response based on the data it was trained upon.  

Why are AI hallucinations a problem?

Despite the term indicating it might be a rare phenomenon, hallucinations are far more likely than accurate or factual results as the AI models used in LLMs are merely predictive and focus on the most probable text or outcome, rather than factual accuracy.

Given the widespread use of generative AI tools in the workplace employees are becoming significantly more likely to encounter an AI hallucination. Furthermore, if these fabricated hallucination responses are taken at face value, they could cause significant issues for an organization.

Use of generative AI in software development

Software developers may use generative AI for recommendations on how to optimize their scripts or code, or to find packages to import into their code for various uses. Software developers may ask LLMs for recommendations on specific pieces of code or how to solve a specific problem, which will likely lead to a third-party package. It is possible that packages recommended by generative AI tools could represent AI hallucinations and the packages may not have been published, or, more accurately, the packages may not have been published prior to the date at which the training data for the model halts. If these hallucinations result in common suggestions of a non-existent package, and the developer copies the code snippet wholesale, this may leave the exchanges vulnerable to attack.

Research conducted by Vulcan revealed the prevalence of AI hallucinations when ChatGPT is asked questions related to coding. After sourcing a sample of commonly asked coding questions from Stack Overflow, a question-and-answer website for programmers, researchers queried ChatGPT (in the context of Node.js and Python) and reviewed its responses. In 20% of the responses provided by ChatGPT pertaining to Node.js at least one un-published package was included, whilst the figure sat at around 35% for Python [4].

Hallucinations can be unpredictable, but would-be attackers are able to find packages to create by asking generative AI tools generic questions and checking whether the suggested packages exist already. As such, attacks using this vector are unlikely to target specific organizations, instead posing more of a widespread threat to users of generative AI tools.

Malicious packages as attack vectors

Although AI hallucinations can be unpredictable, and responses given by generative AI tools may not always be consistent, malicious actors are able to discover AI hallucinations by adopting the approach used by Vulcan. This allows hallucinated packages to be used as attack vectors. Once a malicious actor has discovered a hallucination of an un-published package, they are able to create a package with the same name and include a malicious payload, before publishing it. This is known as a malicious package.

Malicious packages could also be recommended by generative AI tools in the form of pre-existing packages. A user may be recommended a package that had previously been confirmed to contain malicious content, or a package that is no longer maintained and, therefore, is more vulnerable to hijack by malicious actors.

In such scenarios it is not necessary to manipulate the training data (data poisoning) to achieve the desired outcome for the malicious actor, thus a complex and time-consuming attack phase can easily be bypassed.

An unsuspecting software developer may incorporate a malicious package into their code, rendering it harmful. Deployment of this code could then result in compromise and escalation into a full-blown cyber-attack.

Figure 1: Flow diagram depicting the initial stages of an AI Package Hallucination Attack.

For providers of Software-as-a-Service (SaaS) products, this attack vector may represent an even greater risk. Such organizations may have a higher proportion of employed software developers than other organizations of comparable size. A threat actor, therefore, could utilize this attack vector as part of a supply chain attack, whereby a malicious payload becomes incorporated into trusted software and is then distributed to multiple customers. This type of attack could have severe consequences including data loss, the downtime of critical systems, and reputational damage.

How could Darktrace detect an AI Package Hallucination Attack?

In June 2023, Darktrace introduced a range of DETECT™ and RESPOND™ models designed to identify the use of generative AI tools within customer environments, and to autonomously perform inhibitive actions in response to such detections. These models will trigger based on connections to endpoints associated with generative AI tools, as such, Darktrace’s detection of an AI Package Hallucination Attack would likely begin with the breaching of one of the following DETECT models:

  • Compliance / Anomalous Upload to Generative AI
  • Compliance / Beaconing to Rare Generative AI and Generative AI
  • Compliance / Generative AI

Should generative AI tool use not be permitted by an organization, the Darktrace RESPOND model ‘Antigena / Network / Compliance / Antigena Generative AI Block’ can be activated to autonomously block connections to endpoints associated with generative AI, thus preventing an AI Package Hallucination attack before it can take hold.

Once a malicious package has been recommended, it may be downloaded from GitHub, a platform and cloud-based service used to store and manage code. Darktrace DETECT is able to identify when a device has performed a download from an open-source repository such as GitHub using the following models:

  • Device / Anomalous GitHub Download
  • Device / Anomalous Script Download Followed By Additional Packages

Whatever goal the malicious package has been designed to fulfil will determine the next stages of the attack. Due to their highly flexible nature, AI package hallucinations could be used as an attack vector to deliver a large variety of different malware types.

As GitHub is a commonly used service by software developers and IT professionals alike, traditional security tools may not alert customer security teams to such GitHub downloads, meaning malicious downloads may go undetected. Darktrace’s anomaly-based approach to threat detection, however, enables it to recognize subtle deviations in a device’s pre-established pattern of life which may be indicative of an emerging attack.

Subsequent anomalous activity representing the possible progression of the kill chain as part of an AI Package Hallucination Attack could then trigger an Enhanced Monitoring model. Enhanced Monitoring models are high-fidelity indicators of potential malicious activity that are investigated by the Darktrace analyst team as part of the Proactive Threat Notification (PTN) service offered by the Darktrace Security Operation Center (SOC).

Conclusion

Employees are often considered the first line of defense in cyber security; this is particularly true in the face of an AI Package Hallucination Attack.

As the use of generative AI becomes more accessible and an increasingly prevalent tool in an attacker’s toolbox, organizations will benefit from implementing company-wide policies to define expectations surrounding the use of such tools. It is simple, yet critical, for example, for employees to fact check responses provided to them by generative AI tools. All packages recommended by generative AI should also be checked by reviewing non-generated data from either external third-party or internal sources. It is also good practice to adopt caution when downloading packages with very few downloads as it could indicate the package is untrustworthy or malicious.

As of September 2023, ChatGPT Plus and Enterprise users were able to use the tool to browse the internet, expanding the data ChatGPT can access beyond the previous training data cut-off of September 2021 [5]. This feature will be expanded to all users soon [6]. ChatGPT providing up-to-date responses could prompt the evolution of this attack vector, allowing attackers to publish malicious packages which could subsequently be recommended by ChatGPT.

It is inevitable that a greater embrace of AI tools in the workplace will be seen in the coming years as the AI technology advances and existing tools become less novel and more familiar. By fighting fire with fire, using AI technology to identify AI usage, Darktrace is uniquely placed to detect and take preventative action against malicious actors capitalizing on the AI boom.

Credit to Charlotte Thompson, Cyber Analyst, Tiana Kelly, Analyst Team Lead, London, Cyber Analyst

References

[1] https://seo.ai/blog/chatgpt-user-statistics-facts

[2] https://darktrace.com/news/darktrace-addresses-generative-ai-concerns

[3] https://darktrace.com/news/darktrace-email-defends-organizations-against-evolving-cyber-threat-landscape

[4] https://vulcan.io/blog/ai-hallucinations-package-risk?nab=1&utm_referrer=https%3A%2F%2Fwww.google.com%2F

[5] https://twitter.com/OpenAI/status/1707077710047216095

[6] https://www.reuters.com/technology/openai-says-chatgpt-can-now-browse-internet-2023-09-27/

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.
Author
Charlotte Thompson
Cyber Analyst
Tiana Kelly
Deputy Team Lead, London & Cyber Analyst
Book a 1-1 meeting with one of our experts
Share this article

More in this series

No items found.

Blog

/

December 11, 2024

/
No items found.

Company Shuts Down Cyber-attacks with “Flawless” Detection and Response from Darktrace

Default blog imageDefault blog image

Growing pains: Balancing efficiency with risk  

This organization has recently scaled its operations, and numerous acquisitions have significantly boosted the organization’s capabilities and growth. However, this also creates work and high expectations for the organization’s IT and security teams. Within 12 months of an acquisition, the teams must fully integrate each new business onto the company’s platform. “A huge piece of that integration plan is rolling out our security controls,” said the CISO. “While our goal is to connect those facilities up as quickly as possible to drive efficiency, we also need to implement the proper security controls to protect the enterprise.”

Gap beyond the perimeter  

The organization had established strong security measures to safeguard its perimeter; however, the CISO identified a critical gap in real-time network monitoring. If the perimeter were breached, threats were only discovered after an endpoint was compromised and the issue was manually reported.

As digital transformation progresses, the need to adopt advanced technologies is becoming essential, particularly as organizations begin to open up operational environments to greater connectivity. Many processes still rely on traditional methods, and integrating innovative solutions could drive significant improvements in efficiency and productivity. “We’re committed to adopting cutting-edge technologies,” the CISO explained. “But we understood that without more robust network security controls, opening up our operational environments would expose us to heightened risks, including advanced threats like ransomware.”

Building a layered, proactive security strategy with Darktrace  

To close the gap beyond the perimeter, the company embarked on a free trial with Darktrace. The CISO recalls: “The trials were fantastic. It was obvious that Darktrace was exactly what we needed. The Darktrace team was also very knowledgeable and helpful throughout the process, which was impressive.”  

Today, the organization is using a combination of Darktrace solutions for its layered security approach, including:

Detecting unusual behavior with AI  

Darktrace’s use of machine learning and Self-Learning AI is one of the reasons the company chose Darktrace. Instead of teaching an AI system what an ‘attack’ looks like, training it on large data lakes of thousands of organizations’ data, Darktrace AI learns from the company’s own unique data and user activity to learn and create baseline models of what ‘normal’ looks like for their business.

Darktrace can then detect subtle deviations and unusual activity that signals a possible threat. “That fascinated us because what it really means is this technology doesn’t need to know about every single threat because the threat itself isn’t important, it’s the behavior of the activity that’s important. That capability is unique when it when it comes to threat detection,” said the CISO.

Identifying and mitigating high-impact attack paths

The security team appreciated that with Darktrace they could take a more proactive approach to security by exposing high-risk attack paths through modeling and AI risk assessments. Darktrace / Proactive Exposure Management gives them visibility into vulnerable entry points and assets, identifies active risks, and prioritizes the most important security issues to be addressed.

“Specific users and assets within our business have a higher risk of being targeted by a cyber-attack, for example our executives,” said the CISO. “With Darktrace, we get an adversarial view of our risk. We can see the attack path around those potential targets and proactively take measures to mitigate that vulnerability and prevent an attack.”

Driving up productivity while putting the brakes on cyber-attacks  

The security team collaborated with Darktrace to fine tune the models that really fit their business. With Darktrace now automating most of their threat detection and response efforts, productivity has soared, the security team is now focused on delivering greater value to the business and, most importantly, Darktrace proved it could quickly detect and shut down a major cyber-attack–and do so without impacting business operations.

Fueling team productivity with automation and AI

Prior to using Darktrace, the security team had little visibility into potential risks beyond the perimeter. Today, the team has full control and visibility over the network. “My team is now spending 80-90% of their time doing proactive work because Darktrace is managing the vast majority of our detect and response needs. The team really has faith in the Darktrace system,” said the CISO.  

With less time spent on low-level manual tasks, the security team can now focus on higher priority initiatives. For example, they have expanded their internal vulnerability assessments across the entire group. The team couldn’t focus on this additional audit and vulnerability management work if Darktrace wasn’t taking care of most of their security monitoring. “Darktrace has allowed us to move on to these additional kinds of governance projects that we otherwise would have to hire an army of staff to get through”.

Stopping email threats in their tracks

Using Darktrace / EMAIL, the company has identified and blocked a significant percentage of emails that were making it past their native email filters. “Darktrace is especially good at detecting impersonation emails, and we really appreciate its ability to automatically remove suspicious emails directly from a user’s inbox. It adds an extra level of confidence,” said the CISO.

Self-Learning AI understands anomalies within unique communication patterns to stop known and unknown threats. For example, when an employee sent an email to a brand new domain, Darktrace identified the behavior as unusual and inconsistent with baseline models and blocked the email.

Darktrace passes the biggest test of all

In 2024, the company experienced the value of the security system firsthand when attackers exploited a vulnerability in a third-party remote support solution that they was using. This solution provided remote access and tech support capabilities. If successful, the attackers could have infiltrated high-value end points and created their own administrative user, giving them full control over the server.

“We first became aware of the attack when Darktrace notified us of unusual behavior coming from the remote support server,” said the CISO. The attackers were attempting to put backdoors onto the service with the intent of selling access to the highest bidder who would then install ransomware on their servers. It all happened very quickly, as the attackers tried to connect to the internal network and other servers, while also firing off a host of other actions, like PowerShell commands, to escalate their privileges.  

“Darktrace worked flawlessly. There was no chance that ransomware was ever going to come in,” the CISO said. “Even though there was no signature to really look at, Darktrace realized this was not normal behavior for this server, shutting down connections and doing everything it could do to stop the attack.” Within eight hours, the security team identified and stopped the attack, severed its connection to the third-party solution, and completed additional analysis and clean-up. “In addition to our own investigation, third parties like our external SOC and legal department also confirmed that Darktrace performed as expected. We were able to report back to the executive team that there was zero risk that any data or systems were compromised.”

Post-attack, there was no need to make any changes to Darktrace. The team consistently reviews its models and baselines, often collaborating with Darktrace to make adjustments when needed to continuously improve performance. “Because of this relationship and constant engagement with Darktrace’s technical teams, we didn't have to go back and ask: ‘why wasn’t this updated’ or ‘why didn’t this model work.’ The models worked.”

His advice to other organizations facing similar challenges? First, focus on updating, patching, and vulnerability management, and act quickly when vulnerabilities are identified. His second piece of advice: “have an automated detection system like Darktrace in place so you can respond at the speed that these attacks evolve. Humans can no longer keep up with a scripted attack as it moves around and tries to compromise items on your network. You need the right technology to fight these types of attacks.”

Dynamic capabilities for a dynamic future

Real-time playbooks

With a proactive, enterprise-wide security strategy in place, the CISO now has the time to think about future projects and innovations. He’s particularly interested in the idea of generating playbooks on the fly in response to real-time events. He believes cyber-attacks are far too varied for a static playbook to be useful; when an attack strikes, teams need to quickly understand exactly what’s in front of them and how to shut it down. “This fits into our future cybersecurity strategy, and Darktrace is the only company I’ve seen talking about building playbooks dynamically. This kind of technology would really help bring our cybersecurity strategy full circle.”

“Darktrace ’s technology, experience and expertise is helping us staying ahead of cyber-attacks, minimizing our risk and driving greater productivity for our team,” said the CISO. In collaboration with Darktrace, the team have created a security foundation that is both powerful and agile. “While Darktrace is detecting and responding to attacks targeting our business today, we know that it’s always learning, adapting and scaling to ensure we’re protected tomorrow. That gives me peace of mind and the freedom to focus on our future.”

Download the Darktrace / NETWORK Solution Brief

Darktrace / NETWORK solution brief screenshot

Protect in real time: Defend against known and emerging threats without relying on historical data or external intelligence.

Full visibility: Gain comprehensive insights across all network environments, including on-premises, cloud, and remote devices.

AI-powered efficiency: Streamline incident response with AI automation, saving time and resources while ensuring minimal disruption to operations.

Continue reading
About the author
The Darktrace Community

Blog

/

December 11, 2024

/
No items found.

Darktrace is Positioned as a Leader in the IDC MarketScape: Worldwide Network Detection and Response 2024 Vendor Assessment

Default blog imageDefault blog image

Darktrace is pleased to announce that we have been positioned as a Leader in the IDC MarketScape: Worldwide Network Detection and Response 2024 Vendor Assessment. We believe this further highlights Darktrace’s position as a pioneer in the NDR market and follows similar recognition from KuppingerCole, who recently named Darktrace as an Overall Leader, Product Leader, Market Leader and Innovation Leader in the KuppingerCole Leadership Compass: Network Detection and Response (2024).

Network Detection and Response (NDR) solutions are uniquely positioned to provide visibility over the core hub of a business and employee activity, analyzing North-South and East-West traffic to identify threats across the modern network. NDR provides a rich and true source of anomalies and goes beyond process level data that is relied on by Endpoint Detection and Response (EDR) agents that do not provide network level visibility and can be misconfigured at any time.1

Metadata from network traffic can be used to detect a variety of different threats based on events such as anomalous port usage, unusual upload/download activity, impossible travel and many other activities. This has been accelerated by the increased usage of user behavioral analytics (UBA) in network security, which establishes statistical baselines about network entities and highlights deviations from expected activity.1

Darktrace is recognized as a Leader in the IDC MarketScape due to our leadership in the market and our pioneering leadership in AI over the past decade, alongside a variety of other unique differentiators and innovations in the NDR industry.

Darktrace / NETWORK™ delivers full visibility, real time threat detection and Autonomous Response capabilities across an organization’s on-premises, cloud, hybrid and virtual environments, including remote worker endpoints.

Unique Approach to AI

Most NDR vendors and network security tools such as IDS/IPS rely on detecting known attacks with historical data and supervised machine learning, leaving organizations blind and vulnerable to novel threats such as zero-days, variants of known attacks, supply chain attacks and insider threats.

These vendors also tend to apply AI models that are trained globally, and are not unique to each organization’s environment, which creates a high number of false positives and alerts that ultimately lack business context.

The IDC MarketScape recognizes that Darktrace takes a differentiated approach in the market with regards to delivering network detection and response capabilities, noting; “Darktrace is unique in that it does not rely on rules and signatures but rather learns what constitutes as normal for an organization and generates alerts when there is a deviation.”1

Darktrace / NETWORK achieves this through the use of Self-Learning AI and unsupervised machine learning to understand what is normal network behavior, continuously analyzing, mapping and modeling every connection to create a full picture of devices, identities, connections and potential attack paths. Darktrace Self-Learning AI autonomously optimizes itself to cut through the noise and quickly surface genuine, prioritized network security incidents – significantly reducing false positives and removing the hassle of needing to continually tuning alerts manually.

Darktrace’s unique approach to AI also extends to the investigation and triage of network alerts with Cyber AI Analyst. Unlike a chat or prompt based LLM, Cyber AI Analyst investigates all relevant alerts in an environment, including third party alerts, autonomously forming hypotheses and reaching conclusions just like a human analyst would, accelerating SOC Level 2 analyses of incidents by 10x. Cyber AI Analyst also typically providing SOC teams with up to 50,000 additional hours annually of Level 2 analysis producing high level alerts and written reporting, transforming security operations.2

Darktrace also uses its deep understanding of what is normal for a network to identify suspicious behavior, leveraging Autonomous Response capabilities to shut down both known and novel threats in real time, taking targeted actions without disrupting business operations. Darktrace / NETWORK is the only NDR solution that can autonomously enforce a pattern of life based on what is normal for a standalone device or group of peers, rapidly containing and disarming threats based on the overall context of the environment and a granular understanding of what is normal for a device or user – instead of relying on historical attack data.

Continued NDR Market Leadership

Darktrace has been recognized as a Leader in the NDR market, and the IDC MarketScape listed a variety of strengths:

  • Darktrace achieves roughly one-fifth of all global NDR revenue. This is important because other IT and cybersecurity solutions providers necessarily want to have integration with Darktrace.
  • The AI algorithms that Darktrace uses for NDR have had 10 years of deployments, tuning, and learning to draw from.
  • Darktrace is available as a SaaS, as an enterprise license, and as physical, hybrid, or virtual appliances. Darktrace also offers an endpoint agent and visibility into VPN and ZTNA.
  • Darktrace integrates with 30+ different interfaces including SIEM, SOAR, XDR platforms, IT ticketing solutions, and their own dashboards. The Darktrace Threat Visualizer highlights events and incidents from the entire deployment including cloud, apps, email, endpoint, zero trust, network, and OT.
  • Darktrace / NETWORK charts the progress that the SOC is making over time with key metrics such as MTTD/MTTR, alerts generated and processed, and other criteria.
  • Darktrace reported coverage of 14 MITRE ATT&CK categories, 158 techniques, and 184 subtechniques

Proactive Network Resilience

The IDC MarketScape notes, “Ultimately, NDR shines as a standalone detection and response technology but is especially powerful when combined with other platforms. NDR in combination with other control points such as endpoint, data, identity, and application provides the proper context when winnowing alerts and trying to uncover a single source of truth.” . Darktrace comprehensively addresses this as part of the ActiveAI Security Platform, by combining network alerts with data from / EMAIL, / IDENTITY, / ENDPOINT, / CLOUD and / OT, providing deeper contextual analysis for each network alert and automatically enriching investigations.

Darktrace also goes beyond NDR solutions with capabilities that are closely linked to our NDR offering, helping clients to achieve and maintain a state of proactive network resilience:

  • Darktrace / Proactive Exposure Management – look beyond just CVE risks to discover, prioritize and validate risks by business impact and how to address them early, reducing the number of real threats that security teams need to handle.
  • Darktrace / Incident Readiness & Recovery – lets teams respond in the best way to each incident and proactively test their familiarity and effectiveness of IR workflows with sophisticated incident simulations based on their own analysts and assets.

Together, these solutions allow Darktrace / NETWORK to go beyond the traditional approach to NDR and shift teams to a more hardened and proactive stance.

Protecting Clients with Continued Innovation

Darktrace invests heavily in Research and Development to continue providing customers with market-leading NDR capabilities and innovations, which was reflected in our position in the Leader category of the MarketScape report for both capabilities and strategy. We are led by the needs and challenges of our customers, which serve as the driving force behind our continued innovation and leadership in the NDR market. The IDC MarketScape report underlines this approach with the following feedback presented by Darktrace customers:

“A customer intimated that 99% of their detections were OOTB with little need to tune or define parameters.”
“A customer reported that it had early warnings for adversarial tactics such as suspicious SMB scanning, suspicious remote execution, remote desktop protocol (RDP) scanning, data exfiltration, C2C, LDAP query, and suspicious Kerberos activity.”
“The client could use Regex to determine if suspicious behavior was found elsewhere on the network.”

Thousands of customers around the world across all industries and sectors rely on Darktrace / NETWORK to protect against known and novel threats. From the latest vulnerabilities in network hardware to sophisticated new strains of ransomware and everything in-between, Darktrace helps clients detect and respond to all types of threats affecting their networks and avoid business disruption, even from the latest attacks.

Find out more about the unique capabilities of Darktrace / NETWORK and our application of AI in network security in the IDC MarketScape excerpt.

References

  1. IDC MarketScape: Worldwide Network Detection and Response 2024 Vendor Assessment (Doc #US51752324, November 2024)
  2. Darktrace Cyber AI Analyst Customer Fleet Data
Continue reading
About the author
Mikey Anderson
Product Manager, Network Detection & Response
Your data. Our AI.
Elevate your network security with Darktrace AI