Blog

Einblicke in das SOC-Team

Exploring AI Threats: Package Hallucination Attacks

Standard-BlogbildStandard-BlogbildStandard-BlogbildStandard-BlogbildStandard-BlogbildStandard-Blogbild
30
Oct 2023
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).

Schlussfolgerung

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/

EINBLICKE IN DAS SOC-Team
Darktrace Cyber-Analysten sind erstklassige Experten für Threat Intelligence, Threat Hunting und Incident Response. Sie bieten Tausenden von Darktrace Kunden auf der ganzen Welt rund um die Uhr SOC-Support. Einblicke in das SOC-Team wird ausschließlich von diesen Experten verfasst und bietet Analysen von Cyber-Vorfällen und Bedrohungstrends, die auf praktischen Erfahrungen in diesem Bereich basieren.
AUTOR
ÜBER DEN AUTOR
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
ANWENDUNGSFÄLLE
Keine Artikel gefunden.
COre-Abdeckung

More in this series

Keine Artikel gefunden.

Blog

E-Mail

How to Protect your Organization Against Microsoft Teams Phishing Attacks

Standard-BlogbildStandard-Blogbild
21
May 2024

The problem: Microsoft Teams phishing attacks are on the rise

Around 83% of Fortune 500 companies rely on Microsoft Office products and services1, with Microsoft Teams and Microsoft SharePoint in particular emerging as critical platforms to the business operations of the everyday workplace. Researchers across the threat landscape have begun to observe these legitimate services being leveraged more and more by malicious actors as an initial access method.

As Teams becomes a more prominent feature of the workplace many employees rely on it for daily internal and external communication, even surpassing email usage in some organizations. As Microsoft2 states, "Teams changes your relationship with email. When your whole group is working in Teams, it means you'll all get fewer emails. And you'll spend less time in your inbox, because you'll use Teams for more of your conversations."

However, Teams can be exploited to send targeted phishing messages to individuals either internally or externally, while appearing legitimate and safe. Users might receive an external message request from a Teams account claiming to be an IT support service or otherwise affiliated with the organization. Once a user has accepted, the threat actor can launch a social engineering campaign or deliver a malicious payload. As a primarily internal tool there is naturally less training and security awareness around Teams – due to the nature of the channel it is assumed to be a trusted source, meaning that social engineering is already one step ahead.

Screenshot of a Microsoft Teams message request from a Midnight Blizzard-controlled account (courtesy of Microsoft)
Figure 1: Screenshot of a Microsoft Teams message request from a Midnight Blizzard-controlled account (courtesy of Microsoft)

Microsoft Teams Phishing Examples

Microsoft has identified several major phishing attacks using Teams within the past year.

In July 2023, Microsoft announced that the threat actor known as Midnight Blizzard – identified by the United States as a Russian state-sponsored group – had launched a series of phishing campaigns via Teams with the aim of stealing user credentials. These attacks used previously compromised Microsoft 365 accounts and set up new domain names that impersonated legitimate IT support organizations. The threat actors then used social engineering tactics to trick targeted users into sharing their credentials via Teams, enabling them to access sensitive data.  

At a similar time, threat actor Storm-0324 was observed sending phishing lures via Teams containing links to malicious SharePoint-hosted files. The group targeted organizations that allow Teams users to interact and share files externally. Storm-0324’s goal is to gain initial access to hand over to other threat actors to pursue more dangerous follow-on attacks like ransomware.

For a more in depth look at how Darktrace stops Microsoft Teams phishing read our blog: Don’t Take the Bait: How Darktrace Keeps Microsoft Teams Phishing Attacks at Bay

The market: Existing Microsoft Teams security solutions are insufficient

Microsoft’s native Teams security focuses on payloads, namely links and attachments, as the principal malicious component of any phishing. These payloads are relatively straightforward to detect with their experience in anti-virus, sandboxing, and IOCs. However, this approach is unable to intervene before the stage at which payloads are delivered, before the user even gets the chance to accept or deny an external message request. At the same time, it risks missing more subtle threats that don’t include attachments or links – like early stage phishing, which is pure social engineering – or completely new payloads.

Equally, the market offering for Teams security is limited. Security solutions available on the market are always payload-focused, rather than taking into account the content and context in which a link or attachment is sent. Answering questions like:

  • Does it make sense for these two accounts to speak to each other?
  • Are there any linguistic indicators of inducement?

Furthermore, they do not correlate with email to track threats across multiple communication environments which could signal a wider campaign. Effectively, other market solutions aren’t adding extra value – they are protecting against the same types of threats that Microsoft is already covering by default.

The other aspect of Teams security that native and market solutions fail to address is the account itself. As well as focusing on Teams threats, it’s important to analyze messages to understand the normal mode of communication for a user, and spot when a user’s Teams activity might signal account takeover.

The solution: How Darktrace protects Microsoft Teams against sophisticated threats

With its biggest update to Darktrace/Email ever, Darktrace now offers support for Microsoft Teams. With that, we are bringing the same AI philosophy that protects your email and accounts to your messaging environment.  

Our Self-Learning AI looks at content and context for every communication, whether that’s sent in an email or Teams message. It looks at actual user behavior, including language patterns, relationship history of sender and recipient, tone and payloads, to understand if a message poses a threat. This approach allows Darktrace to detect threats such as social engineering and payloadless attacks using visibility and forensic capabilities that Microsoft security doesn’t currently offer, as well as early symptoms of account compromise.  

Unlike market solutions, Darktrace doesn’t offer a siloed approach to Teams security. Data and signals from Teams are shared across email to inform detection, and also with the wider Darktrace ActiveAI security platform. By correlating information from email and Teams with network and apps security, Darktrace is able to better identify suspicious Teams activity and vice versa.  

Interested in the other ways Darktrace/Email augments threat detection? Read our latest blog on how improving the quality of end-user reporting can decrease the burden on the SOC. To find our more about Darktrace's enduring partnership with Microsoft, click here.

References

[1] Essential Microsoft Office Statistics in 2024

[2] Microsoft blog, Microsoft Teams and email, living in harmony, 2024

Continue reading
About the author
Carlos Gray
Product Manager

Blog

Einblicke in das SOC-Team

Don’t Take the Bait: How Darktrace Keeps Microsoft Teams Phishing Attacks at Bay

Standard-BlogbildStandard-Blogbild
20
May 2024

Social Engineering in Phishing Attacks

Faced with increasingly cyber-aware endpoint users and vigilant security teams, more and more threat actors are forced to think psychologically about the individuals they are targeting with their phishing attacks. Social engineering methods like taking advantage of the human emotions of their would-be victims, pressuring them to open emails or follow links or face financial or legal repercussions, and impersonating known and trusted brands or services, have become common place in phishing campaigns in recent years.

Phishing with Microsoft Teams

The malicious use of the popular communications platform Microsoft Teams has become widely observed and discussed across the threat landscape, with many organizations adopting it as their primary means of business communication, and many threat actors using it as an attack vector. As Teams allows users to communicate with people outside of their organization by default [1], it becomes an easy entry point for potential attackers to use as a social engineering vector.

In early 2024, Darktrace/Apps™ identified two separate instances of malicious actors using Microsoft Teams to launch a phishing attack against Darktrace customers in the Europe, the Middle East and Africa (EMEA) region. Interestingly, in this case the attackers not only used a well-known legitimate service to carry out their phishing campaign, but they were also attempting to impersonate an international hotel chain.

Despite these attempts to evade endpoint users and traditional security measures, Darktrace’s anomaly detection enabled it to identify the suspicious phishing messages and bring them to the customer’s attention. Additionally, Darktrace’s autonomous response capability, was able to follow-up these detections with targeted actions to contain the suspicious activity in the first instance.

Darktrace Coverage of Microsoft Teams Phishing

Chats Sent by External User and Following Actions by Darktrace

On February 29, 2024, Darktrace detected the presence of a new external user on the Software-as-a-Service (SaaS) environment of an EMEA customer for the first time. The user, “REDACTED@InternationalHotelChain[.]onmicrosoft[.]com” was only observed on this date and no further activities were detected from this user after February 29.

Later the same day, the unusual external user created its first chat on Microsoft Teams named “New Employee Loyalty Program”. Over the course of around 5 minutes, the user sent 63 messages across 21 different chats to unique internal users on the customer’s SaaS platform. All these chats included the ‘foreign tenant user’ and one of the customer’s internal users, likely in an attempt to remain undetected. Foreign tenant user, in this case, refers to users without access to typical internal software and privileges, indicating the presence of an external user.

Darktrace’s detection of unusual messages being sent by a suspicious external user via Microsoft Teams.
Figure 1: Darktrace’s detection of unusual messages being sent by a suspicious external user via Microsoft Teams.
Advanced Search results showing the presence of a foreign tenant user on the customer’s SaaS environment.
Figure 2: Advanced Search results showing the presence of a foreign tenant user on the customer’s SaaS environment.

Darktrace identified that the external user had connected from an unusual IP address located in Poland, 195.242.125[.]186. Darktrace understood that this was unexpected behavior for this user who had only previously been observed connecting from the United Kingdom; it further recognized that no other users within the customer’s environment had connected from this external source, thereby deeming it suspicious. Further investigation by Darktrace’s analyst team revealed that the endpoint had been flagged as malicious by several open-source intelligence (OSINT) vendors.

External Summary highlighting the rarity of the rare external source from which the Teams messages were sent.
Figure 3: External Summary highlighting the rarity of the rare external source from which the Teams messages were sent.

Following Darktrace’s initial detection of these suspicious Microsoft Teams messages, Darktrace's autonomous response was able to further support the customer by providing suggested mitigative actions that could be applied to stop the external user from sending any additional phishing messages.

Unfortunately, at the time of this attack Darktrace's autonomous response capability was configured in human confirmation mode, meaning any autonomous response actions had to be manually actioned by the customer. Had it been enabled in autonomous response mode, it would have been able promptly disrupt the attack, disabling the external user to prevent them from continuing their phishing attempts and securing precious time for the customer’s security team to begin their own remediation procedures.

Darktrace autonomous response actions that were suggested following the ’Large Volume of Messages Sent from New External User’ detection model alert.
Figure 4: Darktrace autonomous response actions that were suggested following the ’Large Volume of Messages Sent from New External User’ detection model alert.

External URL Sent within Teams Chats

Within the 21 Teams chats created by the threat actor, Darktrace identified 21 different external URLs being sent, all of which included the domain "cloud-sharcpoint[.]com”. Many of these URLs had been recently established and had been flagged as malicious by OSINT providers [3]. This was likely an attempt to impersonate “cloud-sharepoint[.]com”, the legitimate domain of Microsoft SharePoint, with the threat actor attempting to ‘typo-squat’ the URL to convince endpoint users to trust the legitimacy of the link. Typo-squatted domains are commonly misspelled URLs registered by opportunistic attackers in the hope of gaining the trust of unsuspecting targets. They are often used for nefarious purposes like dropping malicious files on devices or harvesting credentials.

Upon clicking this malicious link, users were directed to a similarly typo-squatted domain, “InternatlonalHotelChain[.]sharcpoInte-docs[.]com”. This domain was likely made to appear like the SharePoint URL used by the international hotel chain being impersonated.

Redirected link to a fake SharePoint page attempting to impersonate an international hotel chain.
Figure 5: Redirected link to a fake SharePoint page attempting to impersonate an international hotel chain.

This fake SharePoint page used the branding of the international hotel chain and contained a document named “New Employee Loyalty Program”; the same name given to the phishing messages sent by the attacker on Microsoft Teams. Upon accessing this file, users would be directed to a credential harvester, masquerading as a Microsoft login page, and prompted to enter their credentials. If successful, this would allow the attacker to gain unauthorized access to a user’s SaaS account, thereby compromising the account and enabling further escalation in the customer’s environment.

Figure 6: A fake Microsoft login page that popped-up when attempting to open the ’New Employee Loyalty Program’ document.

This is a clear example of an attacker attempting to leverage social engineering tactics to gain the trust of their targets and convince them to inadvertently compromise their account. Many corporate organizations partner with other companies and well-known brands to offer their employees loyalty programs as part of their employment benefits and perks. As such, it would not necessarily be unexpected for employees to receive such an offer from an international hotel chain. By impersonating an international hotel chain, threat actors would increase the probability of convincing their targets to trust and click their malicious messages and links, and unintentionally compromising their accounts.

In spite of the attacker’s attempts to impersonate reputable brands, platforms, Darktrace/Apps was able to successfully recognize the malicious intent behind this phishing campaign and suggest steps to contain the attack. Darktrace recognized that the user in question had deviated from its ‘learned’ pattern of behavior by connecting to the customer’s SaaS environment from an unusual external location, before proceeding to send an unusually large volume of messages via Teams, indicating that the SaaS account had been compromised.

A Wider Campaign?

Around a month later, in March 2024, Darktrace observed a similar incident of a malicious actor impersonating the same international hotel chain in a phishing attacking using Microsoft Teams, suggesting that this was part of a wider phishing campaign. Like the previous example, this customer was also based in the EMEA region.  

The attack tactics identified in this instance were very similar to the previously example, with a new external user identified within the network proceeding to create a series of Teams messages named “New Employee Loyalty Program” containing a typo-squatted external links.

There were a few differences with this second incident, however, with the attacker using the domain “@InternationalHotelChainExpeditions[.]onmicrosoft[.]com” to send their malicious Teams messages and using differently typo-squatted URLs to imitate Microsoft SharePoint.

As both customers targeted by this phishing campaign were subscribed to Darktrace’s Proactive Threat Notification (PTN) service, this suspicious SaaS activity was promptly escalated to the Darktrace Security Operations Center (SOC) for immediate triage and investigation. Following their investigation, the SOC team sent an alert to the customers informing them of the compromise and advising urgent follow-up.

Schlussfolgerung

While there are clear similarities between these Microsoft Teams-based phishing attacks, the attackers here have seemingly sought ways to refine their tactics, techniques, and procedures (TTPs), leveraging new connection locations and creating new malicious URLs in an effort to outmaneuver human security teams and conventional security tools.

As cyber threats grow increasingly sophisticated and evasive, it is crucial for organizations to employ intelligent security solutions that can see through social engineering techniques and pinpoint suspicious activity early.

Darktrace’s Self-Learning AI understands customer environments and is able to recognize the subtle deviations in a device’s behavioral pattern, enabling it to effectively identify suspicious activity even when attackers adapt their strategies. In this instance, this allowed Darktrace to detect the phishing messages, and the malicious links contained within them, despite the seemingly trustworthy source and use of a reputable platform like Microsoft Teams.

Credit to Min Kim, Cyber Security Analyst, Raymond Norbert, Cyber Security Analyst and Ryan Traill, Threat Content Lead

Anhang

Darktrace Model Detections

SaaS Model

Large Volume of Messages Sent from New External User

SaaS / Unusual Activity / Large Volume of Messages Sent from New External User

Indicators of Compromise (IoCs)

IoC – Type - Description

https://cloud-sharcpoint[.]com/[a-zA-Z0-9]{15} - Example hostname - Malicious phishing redirection link

InternatlonalHotelChain[.]sharcpolnte-docs[.]com – Hostname – Redirected Link

195.242.125[.]186 - External Source IP Address – Malicious Endpoint

MITRE Tactics

Tactic – Technique

Phishing – Initial Access (T1566)

References

[1] https://learn.microsoft.com/en-us/microsoftteams/trusted-organizations-external-meetings-chat?tabs=organization-settings

[2] https://www.virustotal.com/gui/ip-address/195.242.125.186/detection

[3] https://www.virustotal.com/gui/domain/cloud-sharcpoint.com

Continue reading
About the author
Min Kim
Cyber Security Analyst
Our ai. Your data.

Elevate your cyber defenses with Darktrace AI

Starten Sie Ihren kostenlosen Test
Darktrace AI protecting a business from cyber threats.