October 3, 2024

From Call to Compromise: Darktrace’s Response to a Vishing-Induced Network Attack

When a remote user fell victim to a vishing attack, allowing a malicious actor to gain access to a customer network, Darktrace swiftly detected the intrusion and responded effectively. This prompt action prevented any data loss and reinforced trust in Darktrace’s robust security measures.

Written by

Rajendra Rushanth

Cyber Analyst

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

Rajendra Rushanth

Cyber Analyst

Oct 2024

What is vishing?

Vishing, or voice phishing, is a type of cyber-attack that utilizes telephone devices to deceive targets. Threat actors typically use social engineering tactics to convince targets that they can be trusted, for example, by masquerading as a family member, their bank, or trusted a government entity. One method frequently used by vishing actors is to intimidate their targets, convincing them that they may face monetary fines or jail time if they do not provide sensitive information.

What makes vishing attacks dangerous to organizations?

Vishing attacks utilize social engineering tactics that exploit human psychology and emotion. Threat actors often impersonate trusted entities and can make it appear as though a call is coming from a reputable or known source. These actors often target organizations, specifically their employees, and pressure them to obtain sensitive corporate data, such as privileged credentials, by creating a sense of urgency, intimidation or fear. Corporate credentials can then be used to gain unauthorized access to an organization’s network, often bypassing traditional security measures and human security teams.

Darktrace’s coverage of vishing attack

On August 12, 2024, Darktrace / NETWORK identified malicious activity on the network of a customer in the hospitality sector. The customer later confirmed that a threat actor had gained unauthorized access through a vishing attack. The attacker successfully spoofed the IT support phone number and called a remote employee, eventually leading to the compromise.

Figure 1: Timeline of events in the kill chain of this attack.

Establishing a Foothold

During the call, the remote employee was requested to authenticate via multi-factor authentication (MFA). Believing the caller to be a member of their internal IT support, using the legitimate caller ID, the remote user followed the instructions and confirmed the MFA prompt, providing access to the customer’s network.

This authentication allowed the threat actor to login into the customer’s environment by proxying through their Virtual Private Network (VPN) and gain a foothold in the network. As remote users are assigned the same static IP address when connecting to the corporate environment, the malicious actor appeared on the network using the correct username and IP address. While this stealthy activity might have evaded traditional security tools and human security teams, Darktrace’s anomaly-based threat detection identified an unusual login from a different hostname by analyzing NTLM requests from the static IP address, which it determined to be anomalous.

Observed Activity

On 2024-08-12 the static IP was observed using a credential belonging to the remote user to initiate an SMB session with an internal domain controller, where the authentication method NTLM was used
A different hostname from the usual hostname associated with this remote user was identified in the NTLM authentication request sent from a device with the static IP address to the domain controller
This device does not appear to have been seen on the network prior to this event.

Darktrace, therefore, recognized that this login was likely made by a malicious actor.

Internal Reconnaissance

Darktrace subsequently observed the malicious actor performing a series of reconnaissance activities, including LDAP reconnaissance, device hostname reconnaissance, and port scanning:

The affected device made a 53-second-long LDAP connection to another internal domain controller. During this connection, the device obtained data about internal Active Directory (AD) accounts, including the AD account of the remote user
The device made HTTP GET requests (e.g., HTTP GET requests with the Target URI ‘/nice ports,/Trinity.txt.bak’), indicative of Nmap usage
The device started making reverse DNS lookups for internal IP addresses.

Figure 2: Model alert showing the IP address from which the malicious actor connected and performed network scanning activities via port 9401.

Figure 3: Model Alert Event Log showing the affected device connecting to multiple internal locations via port 9401.

Lateral Movement

The threat actor was also seen making numerous failed NTLM authentication requests using a generic default Windows credential, indicating an attempt to brute force and laterally move through the network. During this activity, Darktrace identified that the device was using a different hostname than the one typically used by the remote employee.

Cyber AI Analyst

In addition to the detection by Darktrace / NETWORK, Darktrace’s Cyber AI Analyst launched an autonomous investigation into the ongoing activity. The investigation was able to correlate the seemingly separate events together into a broader incident, continuously adding new suspicious linked activities as they occurred.

Upon completing the investigation, Cyber AI Analyst provided the customer with a comprehensive summary of the various attack phases detected by Darktrace and the associated incidents. This clear presentation enabled the customer to gain full visibility into the compromise and understand the activities that constituted the attack.

Figure 5: Cyber AI Analyst displaying the observed attack phases and associated model alerts.

Darktrace Autonomous Response

Despite the sophisticated techniques and social engineering tactics used by the attacker to bypass the customer’s human security team and existing security stack, Darktrace’s AI-driven approach prevented the malicious actor from continuing their activities and causing more harm.

Darktrace’s Autonomous Response technology is able to enforce a pattern of life based on what is ‘normal’ and learned for the environment. If activity is detected that represents a deviation from expected activity from, a model alert is triggered. When Darktrace’s Autonomous Response functionality is configured in autonomous response mode, as was the case with the customer, it swiftly applies response actions to devices and users without the need for a system administrator or security analyst to perform any actions.

In this instance, Darktrace applied a number of mitigative actions on the remote user, containing most of the activity as soon as it was detected:

Block all outgoing traffic
Enforce pattern of life
Block all connections to port 445 (SMB)
Block all connections to port 9401

Figure 6: Darktrace’s Autonomous Response actions showing the actions taken in response to the observed activity, including blocking all outgoing traffic or enforcing the pattern of life.

The growing threat of vishing in a remote workforce

This vishing attack underscores the significant risks remote employees face and the critical need for companies to address vishing threats to prevent network compromises. The remote employee in this instance was deceived by a malicious actor who spoofed the phone number of internal IT Support and convinced the employee to perform approve an MFA request. This sophisticated social engineering tactic allowed the attacker to proxy through the customer’s VPN, making the malicious activity appear legitimate due to the use of static IP addresses.

Despite the stealthy attempts to perform malicious activities on the network, Darktrace’s focus on anomaly detection enabled it to swiftly identify and analyze the suspicious behavior. This led to the prompt determination of the activity as malicious and the subsequent blocking of the malicious actor to prevent further escalation.

While the exact motivation of the threat actor in this case remains unclear, the 2023 cyber-attack on MGM Resorts serves as a stark illustration of the potential consequences of such threats. MGM Resorts experienced significant disruptions and data breaches following a similar vishing attack, resulting in financial and reputational damage [1]. If the attack on the customer had not been detected, they too could have faced sensitive data loss and major business disruptions. This incident underscores the critical importance of robust security measures and vigilant monitoring to protect against sophisticated cyber threats.

Insights from Darktrace’s First 6: Half-year threat report for 2024

First 6: half year threat report darktrace screenshot

Darktrace’s First 6: Half-Year Threat Report 2024 highlights the latest attack trends and key threats observed by the Darktrace Threat Research team in the first six months of 2024.

Focuses on anomaly detection and behavioral analysis to identify threats
Maps mitigated cases to known, publicly attributed threats for deeper context
Offers guidance on improving security posture to defend against persistent threats

‍

Appendices

Credit to Rajendra Rushanth (Cyber Security Analyst) and Ryan Traill (Threat Content Lead)

Darktrace Model Detections

Device / Unusual LDAP Bind and Search Activity
Device / Attack and Recon Tools
Device / Network Range Scan
Device / Suspicious SMB Scanning Activity
Device / RDP Scan
Device / UDP Enumeration
Device / Large Number of Model Breaches
Device / Network Scan
Device / Multiple Lateral Movement Model Breaches (Enhanced Monitoring)
Device / Reverse DNS Sweep
Device / SMB Session Brute Force (Non-Admin)

List of Indicators of Compromise (IoCs)

IoC - Type – Description

/nice ports,/Trinity.txt.bak - URI – Unusual Nmap Usage

MITRE ATT&CK Mapping

Tactic – ID – Technique

INITIAL ACCESS – T1200 – Hardware Additions

DISCOVERY – T1046 – Network Service Scanning

DISCOVERY – T1482 – Domain Trust Discovery

RECONNAISSANCE – T1590 – IP Addresses

T1590.002 – DNS

T1590.005 – IP Addresses

RECONNAISSANCE – T1592 – Client Configurations

T1592.004 – Client Configurations

RECONNAISSANCE – T1595 – Scanning IP Blocks

T1595.001 – Scanning IP Blocks

T1595.002 – Vulnerability Scanning

References

[1] https://www.bleepingcomputer.com/news/security/securing-helpdesks-from-hackers-what-we-can-learn-from-the-mgm-breach/

Written by

Rajendra Rushanth

Cyber Analyst

Inside the SOC

Written by

Rajendra Rushanth

Cyber Analyst

•

July 9, 2026

Angel Arribas Lopez

Associate Principal Cyber Analyst

•

July 13, 2026

Nathaniel Jones

VP, Security & AI Strategy, Field CISO

Watch the NIS2 Webinar

Blog

July 13, 2026

Security After Signatures: Operating in a World of Pre‑CVE Disclosure Exploitation, Collapsed Trust Boundaries, and Autonomous Systems

Three shifts have reshaped what it means to defend an enterprise securely.

First, exploitation often begins before defenders have a Common Vulnerabilities and Exposures (CVE) identifier, a security advisory, or an entry in the Cybersecurity and Infrastructure Security Agency's (CISA) Known Exploited Vulnerabilities (KEV) catalog.

Secondly, the trust boundary has moved beyond the network edge into identities, tokens, APIs, and Software-as-a-Service (SaaS) workflows.

Third, an increasing share of business activity is executed through automation, integrations, and AI agent-like systems that can act faster than teams can verify intent.

If your security model still relies on detecting known bad artefacts, triaging isolated alerts, and waiting for confirmation before acting, you are already behind the threat.

This is not a failure of security teams; it’s a failure of the operating model to keep pace with how the environment has changed.

A SOC built around alerts and signatures assumes that malicious activity will eventually surface as an event. In real incidents, however, the decisive evidence is rarely a single event. Instead, it is a chain of individually explainable actions that only appears malicious once you connect the dots across identity, non-human identity, cloud, email, SaaS, operational technology (OT), and network telemetry.

The defenders succeeding today observe behaviors, link them into sequences, understand what those sequences mean, and contain impact before the full story unfolds. That is the operating model the current threat environment demands.

Exploitation before disclosure

The first shift is the straightforward: the time to exploit has dropped to nearly zero.

In one example, Darktrace observed a sequence of subtle but strategically significant anomalies within a customer environment that later aligned with exploitation of CVE‑2025‑0994 in Trimble Cityworks by likely Chinese-nexus threat actors. Behavioral indicators were visible at least 18 days before public disclosure, with related anomalies emerging 40 to 50 days earlier during the intrusion window.

This case illustrates a familiar pattern: clusters of weak‑signal anomalies combing to form an actionable picture of intrusion long before a CVE is published. Such activity reflects long‑horizon, option‑preserving operator models often associated with mature state‑linked activity.

Figure 1: Darktrace’s detection of malicious exploitation of CVE 2025-0994, later tied to Chinese-nexus threat actors targeting critical national infrastructure (CNI) in the US, weeks before public disclosure.

Throughout 2025 and 2026, Darktrace has continued to observe the value of anomaly-based detections across a range of incidents.

CVE	CVE public disclosure date	Darktrace detection date	Days between detection of exploitation and CVE public disclosure
CVE-2025-0994 Trimble Cityworks	2025-02-06	2025-01-19	18 days
CVE-2025-24183 Apache	2025-03-10	2025-02-18	20 days
CVE-2025-10035 Fortra GoAnywhere	2025-09-18	2025-09-11	7 days
CVE-2026-0257 PAN-OS	2026-05-13	—	—

Identity is the real control plane

The second shift is that identity has replaced perimeter as the primary control plane. As Darktrace’s Annual Threat Report 2026 illustrated, identity remains the main challenge in defending against modern intrusions. A clear example is the Adversary-in-the-Middle (AiTM) case published by Darktrace in December 2025. A phishing email led to the compromise of an Office 365 account. Session hijacking bypassed multi-factor authentication (MFA), and the compromised account was used for follow-on phishing and persistence activities including the creation of malicious email rules.

Every step in that sequence mattered. A successful login alone does not prove legitimacy. An inbox rule, on its own, may not appear catastrophic. Mail activity, viewed in isolation, may seem operationally normal. But the behavioral chain tells a different story: credential theft, token abuse, persistence, and onward compromise through a trusted identity.

This is why the question is no longer “Did the user authenticate successfully”. The more important question is, “Does this identity action make sense right now, in this context, given what came before it?” The AiTM case shows how identity can be compromised. In practice, however, attacks rarely remained confined to identity alone.

In another Darktrace case, a compromised SaaS account triggered activity across the email, SaaS, and network layers, including inbox rule changes, phishing propagation, and connections to suspicious infrastructure. Viewed in isolation, none of these events were decisive. Together, however, they formed a behavioral sequence that revealed the intrusion, with the full attack story automatically correlated and surfaced to defenders by Darktrace’s Cyber AI Analyst.

Figure 2: Cyber AI Analyst correlated and appended additional events to the incident, including other users who connected to the suspicious redirect link after outbound phishing emails were sent.

AI accelerates the threat

The third shift is the one many teams still underestimate: trusted tooling, integrations, and AI agent-like systems can create actions that appear legitimate but are strategically dangerous.

The shift becomes clearer when examining how governments are now framing AI risk. In 2026, guidance published by CISA, UK’s National Cyber Security Centre (NCSC) and Five Eyes partners warned that agentic systems expand attack surfaces, accumulate privilege, and can behave in ways that are difficult to predict or explain [1]. The advice is simple: assume unexpected behavior and design controls around it.

The real risk is not AI usage. It is unknown autonomy: systems with credentials, data access, and action paths that can execute workflow steps without sufficient behavioral validation, traceability, or human oversight. Darktrace’s Model Context Protocol (MCP) risk analysis provides a useful framework for understanding this challenge. Over-privileged agents, content injection, and tool abuse become high-consequence risks when connected systems can dynamically retrieve data, execute actions, and communicate externally.

Whether security teams like it or not, AI is already in the enterprise. It will help drive innovation, but it will also be abused, whether accidentally or maliciously. In each of the cases below, AI either scaled the attacker, built the tooling, or existed within the environment as something to exploit or misuse.

1. AI as an Attack Multiplier

In one campaign targeting Mexican government entities, a single operator used commercial AI platforms to generate exploits, automate reconnaissance, and process large volumes of data, compressing work that would traditionally have required an entire team into a single workflow [2].

Darktrace is also observing this trend further down the stack. In one case, Darktrace identified AI-generated malware exploiting React2Shell, where an attacker used a Large Language Model (LLM) to produce working exploit code and deploy it at scale.

[darktrace.com], [darktrace.com] ‍

2. AI as an Attack Surface

Attempted AI exploitation is now appearing within customer environments. In one case involving an automation technology manufacturer, a compromised LLM proxy was seemingly used as a stepping stone to access additional AI services. When that attempt failed, the attacker pivoted to cryptomining.

What is clear is that the AI layer has already become an asset worth probing, exploiting, and pivoting through. It is also clear that defenders benefit from rapidly understanding how these activities connect. In this case, Cyber AI Analyst automatically pieced together the intrusion, while Darktrace’s Managed Threat Detection service alerted to the customer, enabling the activity to be contained before it could progress further.

Figure 3: Cyber AI Analyst's investigation into a compromised LLM proxy that was abused for cryptomining activity.

AI as a trusted but dangerous actor

This does not require a cinematic vision of “rogue AI.” The Salesloft incident provides a more grounded example, where AI and automation operate with legitimate access but served malicious intent. In that case, attackers abused compromised OAuth tokens associated with the Drift AI chat agent to export significant volumes of data from Salesforce environments.

The activity resembled legitimate API usage and relied on trusted SaaS integrations rather than malware or other obvious signs of intrusion. That is precisely the challenge. Traditional security controls are good at detecting forced entry, but far less effective when a trusted application integration behaves in a way that is technically permitted yet operationally harmful.

In these scenarios, the security challenge shifts from validating access to validating behavior.

This is what that looks like in practice: AI-linked identities executing legitimate actions that require behavioral validation rather than access validation.

Figure 4: Darktrace / SECURE AI highlights anomalous activity across AI identities, surfacing critical behavior that requires validation and containment.

Early observations from Darktrace / SECURE AI deployments reinforce this reality. Across Darktrace's observed fleet, AI service connections per deployment increased 13% during the first half of 2026, reaching over 16 million connections overall. The typical organisation now interacts with seven different AI providers, evidence that AI is no longer operating at the edges of the enterprise. It is increasingly woven into day-to-day business activity.

The most common risks are not compromised models or advanced AI attacks. Instead, they stem from employees and business functions exposing sensitive information through entirely legitimate-looking interactions. Darktrace has observed repeated submission of personally identifiable information (PII), tax information, identification documents, and medical data into LLM prompts, alongside widespread use of unsanctioned (shadow) AI services and growing AI activity from mobile devices.

For defenders, the challenge is increasingly one of context: understanding when legitimate business use crosses into material risk, while preserving privacy and user trust.

Conclusion

Across all three shifts, the pattern is the same: behavior precedes understanding. Security teams are not losing because adversaries have become invisible. An increasingly outdated security model assumes that malicious activity will reveal itself cleanly and early. It no longer does.

In 2026 and beyond, defenders win by understanding behavioral sequences, continuously validating trust, and acting before certainty becomes hindsight. That is security after signatures. That is security in the AI era.

Credit to: Daniel Levy, Threat Hunting Data Scientist

Edited by: Ryan Trail, Content Manager

References

[1] https://www.cyber.gov.au/business-government/secure-design/artificial-intelligence/careful-adoption-of-agentic-ai-services

[2]https://www.latimes.com/business/story/2026-02-26/hacker-used-anthropics-claude-ai-to-steal-mexican-government-data

About the author

Nathaniel Jones

VP, Security & AI Strategy, Field CISO

Blog

July 9, 2026

When AI Infrastructure Becomes Part of the Attack Surface

AI Infrastructure and the Evolving Attack Surface

As organizations deploy generative AI into production environments, a new layer of infrastructure has emerged inside enterprise cloud environments: AI gateways.

What is an AI gateway?

AI gateways are systems that sit between users, applications, and foundation models, often holding privileged cloud permissions and managing access to AI services at scale.

Because of that role, AI gateways are becoming an increasingly important part of the enterprise attack surface. A compromise may provide attackers with access not only to compute resources, but also to cloud identities, model services, sensitive prompts, and other connected systems.

This blog examines how Darktrace investigated a compromised AI gateway connected to Amazon Bedrock services that was subsequently observed communicating with cryptomining infrastructure. Based on its configuration and associated Identity and Access Management (IAM) role, the instance appeared to function as a gateway to Amazon Bedrock-hosted AI services. Following suspected compromise activity, the host was observed communicating repeatedly with known cryptomining infrastructure before subsequently being shut down. Darktrace detected and escalated the activity through its Enhanced Monitoring and Managed Threat Detection services.

While the ultimate impact in this case appeared to be unauthorized cryptomining, the incident is notable because of where it occurred. The compromised asset sat at the intersection of cloud infrastructure, identity, and AI services. Recent research has highlighted how AI gateways such as LiteLLM can become attractive targets due to their ability to centralize credentials, model access, and cloud permissions. Although Darktrace found no evidence linking this activity directly to publicly disclosed LiteLLM vulnerabilities, the incident demonstrates why organizations should treat AI infrastructure as part of their critical attack surface rather than as a standalone application tier [1].

Why cryptomining remains a common cloud post-compromise activity

Cryptomining can be a lucrative post-compromise activity in cloud environments. After gaining access to a cloud asset, attackers may deploy mining software to abuse the victim’s compute resources for financial gain. This type of activity is likely to be opportunistic, targeting exposed services, weak credentials, leaked access keys, vulnerable applications, or misconfigured cloud workloads.

A typical cloud cryptomining intrusion may involve:

Identifying exposed or vulnerable cloud infrastructure
Gaining access through exposed services, credentials, or application weaknesses
Downloading and executing mining software
Establishing repeated outbound connectivity to mining pool infrastructure
Continuing to consume compute resources until the activity is detected and disrupted

The notable element in this case is not the cryptomining alone, but where it occurred: on cloud infrastructure supporting AI-related activity. This shows how assets used to enable AI services can still be exposed to familiar cloud compromise risks.

Investigating a compromised AI gateway connected to Amazon Bedrock

On June 12, 2026, Darktrace observed activity consistent with active cryptomining from an Amazon Web Service (AWS) EC2 instance named LiteLLM-Proxy. The instance appeared to support LiteLLM activity and was associated with an instance profile that had access to Amazon Bedrock resources.

AI gateways are designed to centralize access to large language models, often handling authentication, routing, logging, and policy enforcement for AI applications. From a security perspective, they also aggregate cloud permissions, model access, and application workflows into a single control point. As a result, compromise of an AI gateway can have implications beyond the affected host itself.

While the exact initial access vector could not be confirmed, the activity appears to follow a sequence often seen in compromises of internet-facing systems: brute-forced access, payload delivery, and repeated outbound connectivity to mining pool infrastructure.

Stage 1: Internet-exposed SSH enabled initial access

Prior to the observed cryptomining activity, the LiteLLM-Proxy EC2 instance appeared to be externally exposed over SSH, with port 22 open to 0.0.0.0/0.

*Figure 1: Darktrace’s misconfiguration alert EC2 instance allowing all inbound traffic to SSH port 22.*

Prior to the cryptomining activity, Darktrace observed a large volume of inbound connection attempts to the instance over port 22 from external IP addresses, predominantly from 145.241.123[.]102, suggesting brute-force activity [2]. Many of these connections were short-lived, lasting only a few seconds, indicating scanning or failed login attempts.

‍

*Figure 2: Darktrace’s detection of unusual incoming connection attempts to the device over port 22.*

The available telemetry did not confirm whether any inbound SSH connection resulted in successful authentication, preventing this activity from being confirmed as the initial access vector. However, the combination of public SSH exposure, inbound connections from external IP addresses, and subsequent miner activity suggests that SSH was a plausible access path.

Stage 2: XMRig malware downloaded to the AI gateway

Before the first observed connection to the mining pool, the EC2 instance downloaded 3.42 MB of data over an HTTP connection on port 80 to the external endpoint, 185.62.1[.]8, which appears to host a ZIP file containing XMRig crypto-mining malware [3][4]. As host-level logs were not available, Darktrace could not confirm how the miner was executed or whether the earlier SSH activity directly enabled payload delivery. However, the timing of the download, followed shortly by repeated mining pool connectivity, supported the assessment that the instance had been compromised and was being used for unauthorized compute activity.

Stage 3 – Compromised AI gateway communicates with cryptomining infrastructure

Just a few minutes later, Darktrace observed the LiteLLM-Proxy EC2 instance connecting to the hostname pool.hasvault[.]pro over HTTPs on port 443. Following the initial connection, repeated outbound connectivity to the same hostname was observed. This pattern is consistent with active cryptomining pool communication, where a compromised host communicates with mining infrastructure to receive work and submit results.

This activity triggered the Enhanced Monitoring model “Compromise / High Priority Crypto Currency Mining”, which was escalated to the customer by Darktrace’s SOC. The activity was also summarized by Darktrace’s Cyber AI Analyst, which grouped the relevant events into a single investigation narrative, helping to identify the repeated mining pool connectivity from the affected cloud asset.

*Figure 3: Cyber AI Analyst’s investigation of the cryptocurrency mining activity.*

The use of HTTPS over port 443 is notable because, when viewed in isolation, this traffic may not appear inherently suspicious. In this case, however, the destination, volume of connections, and lack of similar activity provided the behavioral context needed to identify the communication as suspicious.

Stage 4: Managed Threat Detection identifies active resource abuse

The cryptomining activity was received by Darktrace’s Managed Threat Detection service and reviewed by Darktrace’s SOC. Following review, the activity was escalated to the customer. This escalation provided the customer with timely notification of active resource abuse in the AWS environment.

Stage 5: Suspicious IAM activity suggests possible cloud credential misuse

Separately, on June 13, Darktrace observed suspicious activity originating from an additional IAM user.

*Figure 4: Darktrace’s Advanced Search highlighting suspicious activity performed by a second IAM user.*

First, the user was observed attempting the “GetSendQuota” event, an action that had not performed by the account within at least the previous three months. Additionally, the source IP address of this command appeared to be 14.176.1[.]47, geolocated in Vietnam, whereas activity for this user had mostly been seen from Amazon IP addresses. Furthermore, the AWS CLI was also observed being used for this activity, which was also unusual for the user. This was detected by the model “IaaS / Unusual Activity / Unusual AWS CLI Activity”.

*Figure 5: Darktrace’s detection of the “GetSendQuota” event.*

Further suspicious activity was observed from the IAM user using the long-term access key. Notably, failed “InvokeModel” and “ListFoundationModels” commands were detected, suggesting attempted interaction with Amazon Bedrock services, including model enumeration or invocation. While this may suggest relation to the LiteLLM compromise observed the previous day, there is insufficient evidence to conclusively link the two events.

The attempted “CreateUser” command was also notable because the requested username appeared low-meaning, which may indicate an attempt to establish persistence by creating a new account. This activity triggered the model “IaaS / Admin / New AWS User Account Creation”.

*Figure 6: Darktrace’s detection of the “CreateUser” event.*

Even without a confirmed link between the two incidents, the IAM activity remains significant. It demonstrates the importance of incorporating workload both telemetry and control-plane telemetry into cloud compromise investigations. While the EC2 cryptomining activity indicated compute resource abuse, the IAM activity suggested potential credential compromise or misuse involving long-term access keys, along with attempted cloud service abuse.

Key lessons for securing AI infrastructure

This incident was notable not because of the cryptomining activity itself, but because of where it occurred. The compromised system appeared to function as an AI gateway with access to Amazon Bedrock services, placing it at the intersection of cloud infrastructure, identity, and AI operations. As organizations deploy AI capabilities into production environments, these platforms are becoming part of the same attack surface that adversaries already target through exposed services, credential theft, and cloud misconfigurations.

While the exact intrusion path could not be confirmed, and no definitive link was established between the compromised workload and the suspicious IAM activity observed during the investigation, both events reinforce a broader reality: AI infrastructure must be secured as part of the wider cloud environment rather than treated as a separate technology stack.

In this case, the most obvious sign of compromise was communication with cryptomining infrastructure. The more important lesson is that Darktrace’s behavioral analysis revealed risk surrounding a privileged AI-enabled asset before the full scope of the incident was understood. As AI gateways increasingly concentrate cloud permissions, model access, and application workflows, defenders will need to focus less on individual alerts and more on understanding how behaviors connect across workloads, identities, and services.

Credit to Angel Arribas Lopez (Associate Principal Cyber Analyst), Nathaniel Jones (Field CISO/VP Threat Research), Emma Foulger (Global Threat Ops), and Mark Turner (Security Researcher)

Edited by Ryan Traill (Content Manager)