Blog
/
/
November 19, 2025

Securing Generative AI: Managing Risk in Amazon Bedrock with Darktrace / CLOUD

Generative AI services like Amazon Bedrock are introducing new risks around access, visibility, and data exposure. This blog explores how Darktrace / CLOUD helps prevent these incidents through deep configuration visibility, privilege analysis, misconfiguration detection, and behavioral anomaly monitoring across Bedrock and SageMaker environments.
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
Adam Stevens
Senior Director of Product, Cloud | Darktrace
securing generative aiDefault blog image
19
Nov 2025

Security risks and challenges of generative AI in the enterprise

Generative AI and managed foundation model platforms like Amazon Bedrock are transforming how organizations build and deploy intelligent applications. From chatbots to summarization tools, Bedrock enables rapid agent development by connecting foundation models to enterprise data and services. But with this flexibility comes a new set of security challenges, especially around visibility, access control, and unintended data exposure.

As organizations move quickly to operationalize generative AI, traditional security controls are struggling to keep up. Bedrock’s multi-layered architecture, spanning agents, models, guardrails, and underlying AWS services, creates new blind spots that standard posture management tools weren’t designed to handle. Visibility gaps make it difficult to know which datasets agents can access, or how model outputs might expose sensitive information. Meanwhile, developers often move faster than security teams can review IAM permissions or validate guardrails, leading to misconfigurations that expand risk. In shared-responsibility environments like AWS, this complexity can blur the lines of ownership, making it critical for security teams to have continuous, automated insight into how AI systems interact with enterprise data.

Darktrace / CLOUD provides comprehensive visibility and posture management for Bedrock environments, automatically detecting and proactively scanning agents and knowledge bases, helping teams secure their AI infrastructure without slowing down expansion and innovation.

A real-world scenario: When access goes too far

Consider a scenario where an organization deploys a Bedrock agent to help internal staff quickly answer business questions using company knowledge. The agent was connected to a knowledge base pointing at documents stored in Amazon S3 and given access to internal services via APIs.

To get the system running quickly, developers assigned the agent a broad execution role. This role granted access to multiple S3 buckets, including one containing sensitive customer records. The over-permissioning wasn’t malicious; it stemmed from the complexity of IAM policy creation and the difficulty of identifying which buckets held sensitive data.

The team assumed the agent would only use the intended documents. However, they did not fully consider how employees might interact with the agent or how it might act on the data it processed.  

When an employee asked a routine question about quarterly customer activity, the agent surfaced insights that included regulated data, revealing it to someone without the appropriate access.

This wasn’t a case of prompt injection or model manipulation. The agent simply followed instructions and used the resources it was allowed to access. The exposure was valid under IAM policy, but entirely unintended.

How Darktrace / CLOUD prevents these risks

Darktrace / CLOUD helps organizations avoid scenarios like unintended data exposure by providing layered visibility and intelligent analysis across Bedrock and SageMaker environments. Here’s how each capability works in practice:

Configuration-level visibility

Bedrock deployments often involve multiple components: agents, guardrails, and foundation models, each with its own configuration. Darktrace / CLOUD indexes these configurations so teams can:

  1. Inspect deployed agents and confirm they are connected only to approved data sources.
  2. Track evaluation job setups and their links to Amazon S3 datasets, uncovering hidden data flows that could expose sensitive information.
  3. Maintain full awareness of all AI components, reducing the chance of overlooked assets introducing risk.

By unifying configuration data across Bedrock, SageMaker, and other AWS services, Darktrace / CLOUD provides a single source of truth for AI asset visibility. Teams can instantly see how each component is configured and whether it aligns with corporate security policies. This eliminates guesswork, accelerates audits, and helps prevent misaligned settings from creating data exposure risks.

 Agents for bedrock relationship views.
Figure 1: Agents for bedrock relationship views

Architectural awareness

Complex AI environments can make it difficult to understand how components interact. Darktrace / CLOUD generates real-time architectural diagrams that:

  1. Visualize relationships between agents, models, and datasets.
  1. Highlight unintended data access paths or risk propagation across interconnected services.

This clarity helps security teams spot vulnerabilities before they lead to exposure. By surfacing these relationships dynamically, Darktrace / CLOUD enables proactive risk management, helping teams identify architectural drift, redundant data connections, or unmonitored agents before attackers or accidental misuse can exploit them. This reduces investigation time and strengthens compliance confidence across AI workloads.

Figure 2: Full Bedrock agent architecture including lambda and IAM permission mapping
Figure 2: Full Bedrock agent architecture including lambda and IAM permission mapping

Access & privilege analysis

IAM permissions apply to every AWS service, including Bedrock. When Bedrock agents assume IAM roles that were broadly defined for other workloads, they often inherit excessive privileges. Without strict least-privilege controls, the agent may have access to far more data and services than required, creating avoidable security exposure. Darktrace / CLOUD:

  1. Reviews execution roles and user permissions to identify excessive privileges.
  2. Flags anomalies that could enable privilege escalation or unauthorized API actions.

This ensures agents operate within the principle of least privilege, reducing attack surface. Beyond flagging risky roles, Darktrace / CLOUD continuously learns normal patterns of access to identify when permissions are abused or expanded in real time. Security teams gain context into why an action is anomalous and how it could affect connected assets, allowing them to take targeted remediation steps that preserve productivity while minimizing exposure.

Misconfiguration detection

Misconfigurations are a leading cause of cloud security incidents. Darktrace / CLOUD automatically detects:

  1. Publicly accessible S3 buckets that may contain sensitive training data.
  2. Missing guardrails in Bedrock deployments, which can allow inappropriate or sensitive outputs.
  3. Other issues such as lack of encryption, direct internet access, and root access to models.  

By surfacing these risks early, teams can remediate before they become exploitable. Darktrace / CLOUD turns what would otherwise be manual reviews into automated, continuous checks, reducing time to discovery and preventing small oversights from escalating into full-scale incidents. This automated assurance allows organizations to innovate confidently while keeping their AI systems compliant and secure by design.

Configuration data for Anthropic foundation model
Figure 3: Configuration data for Anthropic foundation model

Behavioral anomaly detection

Even with correct configurations, behavior can signal emerging threats. Using AWS CloudTrail, Darktrace / CLOUD:

  1. Monitors for unusual data access patterns, such as agents querying unexpected datasets.
  2. Detects anomalous training job invocations that could indicate attempts to pollute models.

This real-time behavioral insight helps organizations respond quickly to suspicious activity. Because it learns the “normal” behavior of each Bedrock component over time, Darktrace / CLOUD can detect subtle shifts that indicate emerging risks, before formal indicators of compromise appear. The result is faster detection, reduced investigation effort, and continuous assurance that AI-driven workloads behave as intended.

Conclusion

Generative AI introduces transformative capabilities but also complex risks that evolve alongside innovation. The flexibility of services like Amazon Bedrock enables new efficiencies and insights, yet even legitimate use can inadvertently expose sensitive data or bypass security controls. As organizations embrace AI at scale, the ability to monitor and secure these environments holistically, without slowing development, is becoming essential.

By combining deep configuration visibility, architectural insight, privilege and behavior analysis, and real-time threat detection, Darktrace gives security teams continuous assurance across AI tools like Bedrock and SageMaker. Organizations can innovate with confidence, knowing their AI systems are governed by adaptive, intelligent protection.

[related-resource]

Learn more about securing AI in the enterprise

Discover how to identify AI-driven risks, so you can secure innovation without exposing the enterprise to new attack surfaces.

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
Adam Stevens
Senior Director of Product, Cloud | Darktrace

More in this series

No items found.

Blog

/

/

June 11, 2026

Cybersecurity for the Sports Sector: The Threats Facing a Digitized Industry in 2026

Sports Stadium cybersecurityDefault blog imageDefault blog image

Securing sporting events in 2026

When you walk into a stadium on game day, you are entering a small smart city. Ticketing, turnstiles, payments, public Wi-Fi for tens of thousands of fans, CCTV, lighting, even the HVAC all run on connected systems. The experience for fans has become unmatched, but that dependency has created a much larger attack surface than people may realize.

Our latest threat research backs that up. In the past year, a survey that Darktrace commissioned found that 84% of respondents from professional sports organizations had at least one cyber incident, and 57% were hit more than once. For a sector that relies on the impact of the live moment, those numbers translate directly into operational risk.

Why sports is a target for cyber attacks

Sport is a highly visible target with fixed timelines, so attackers know exactly when disruption will have the most impact. It also holds valuable data, athlete medical records, contracts, sponsorship deals, which carry financial, reputational, and regulatory risk if exposed. At the same time, delivery depends on a wide set of third parties: ticketing providers, broadcasters, cloud services, stadium technology. Any of those connections can become an entry point. Put visibility, timing, data, and dependency together, and you get an environment where even a small foothold can turn into a visible, time-critical incident.

How attackers target email and identity

Email and identity remain the front door. From October 2025 through March 2026, Darktrace / EMAIL™ detected more than 116,000 phishing emails aimed at sports organizations across our customer base, and our sports customers received 19% more phishing emails than organizations in other sectors. The numbers tell the story:

BY THE NUMBERS

  • 21% of phishing emails were aimed at VIPs.
  • 37% used novel social engineering.
  • 84% of malicious emails passed DMARC authentication

A large proportion of these emails passed authentication checks, which means traditional security controls are no longer a reliable barrier. Attackers are not relying on spoofed domains – they're using legitimate infrastructure and trusted platforms. Behavior matters. Once an account is compromised, the behavior shifts quickly. Login patterns change, inbox rules are created to hide responses, and accounts start being used for internal discovery or further phishing. These aren’t high-noise events. They sit in normal workflows, which is why they’re often missed.

Ransomware tells a similar story. In one case inside a sports deployment, attackers had quietly been moving data to an outside server for a full two weeks before they triggered encryption. By the time the ransom note appeared, the outcome was already set. That sequence shows up consistently is access first, movement next, disruption last. If detection starts at encryption, it’s already too late.

Why AI is an emerging blind spot in sports

The increasing adoption of AI is expanding the potential attack surface. 72% of the security professionals we surveyed expect AI to increase their cyber risk over the next year, and yet 35% are already using or planning to use it in stadium operations, the most critical functions to protect. In addition to prompt injection and AI build risks, shadow AI is becoming a more immediate issue. Staff are already putting sensitive data—performance metrics, scouting reports, contracts, health data—into tools with little or no governance. The upside is clear, but so is the exposure—and it is happening before most organizations have any visibility or control. At the same time, attackers are using the same technology to scale phishing and social engineering. The net effect is simple: more exposure, at higher speed.

How can cybersecurity professionals prepare

Across high profile events, Darktrace’s experience shows that effective cyber defense includes preparation, real‑time visibility, and the ability to respond dynamically and decisively when timing, complexity, and public exposure converge.

There are a few strategic implications for cybersecurity teams:

  • Get behavioral visibility across IT and OT, not just corporate systems.
  • Treat identity as your control plane. Most attacks in this sector start with credentials, not malware. MFA with behavioral detection helps solve that challenge.
  • Control third party and AI access the same way you control your own environment.
  • Rehearse response for live conditions, where decisions happen in minutes. Detection and response need to account for non-ideal conditions when engineers are under pressure and time constrained. In sport, timing is what turns small issues into major incidents. The same activity that would be manageable midweek becomes critical during a live event.

Why 2026 raises the cybersecurity stakes for sports

With the 2026 World Cup about to stretch across three countries and dozens of host cities, the attack surface is wide and the schedule is unforgiving.

Geopolitical signaling is raising the threat profile further. Previous international sporting events have demonstrated that nation‑state actors use the cyber domain to signal intent, influence narratives, or retaliate symbolically. In the context of the 2026 World Cup, Russia’s continued exclusion from international sport, the ongoing conflict in Ukraine, US defensive support to Ukraine, and Iran’s likely participation in the tournament introduce additional motivations for state‑aligned and non‑traditional affiliated actors to operate below the threshold of armed conflict. This doesn’t require new techniques—just the right timing and visibility.

In practice, this comes down to preparation: knowing what normal looks like across IT and OT, controlling third-party access, and spotting when behavior shifts.

In sport, disruption does not build slowly—it happens in real time and in public. By that point, the groundwork has already been set, long before the whistle goes.

About this research

Findings are based on Darktrace threat-research telemetry across sports-sector customer deployments (Q4 2025–Q1 2026) and a survey of 875 IT cybersecurity professionals in the US, UK, Australia, and Germany, fielded by Opinion Matters between May 28 and June 3, 2026. Read the full report for complete methodology, incident analysis, and strategic recommendations.

[related-resource]

Continue reading
About the author
Nathaniel Jones
VP, Security & AI Strategy, Field CISO

Blog

/

OT

/

June 11, 2026

Protecting Stadiums & Events with AI

Default blog imageDefault blog image

Stadium and large public venue operators are confronted with a unique set of cyber security challenges. Often described as a ‘honeypot’ for cyber-criminals, the sports and entertainment industry is an attractive target for threat actors for three main reasons:

  • Modern sports organizations process sensitive and highly valuable data at scale;
  • Sporting events are highly visible and time-critical, operating in front of live audiences with no room for error;
  • Sports organizations rely on sprawling vendor ecosystems and supply chains to deliver broadcast, commerce, fan engagement services, and more.

In a recent Darktrace-commissioned survey, 84% of professional sports organizations reported at least one cyber incident in the past year, and 57% were hit more than once [1]. The potential ramifications of cyber disruption during a large-scale sports event cannot be overstated. A momentary lapse in access to power could bring TV broadcasts to a halt; disruption to access controls could restrict fans from entering the grounds; CCTV outages could increase the risk of criminal behavior and physical injuries. If data is not reliable and stadium machines are outputting the wrong metrics, a venue could become dangerously overcrowded. The barrier between the cyber and physical worlds has long dissolved – cyber-attacks threaten human safety.

In this blog, I explore the key challenges of stadium cyber security and explain the unique capabilities of Self-Learning AI that led me to adopt Darktrace as a head of ICT and cyber security for international venues and events. Over my career I have helped secure football and rugby World Cups, World Athletics Championships and more than 500 events ,and the lessons from each have only sharpened my conviction in this approach.

The access paradox

The biggest challenge lies in the paradox of securing a site where various internal services are provided to a large number of unknown and unmanaged users, suppliers and devices. When it’s game time, or ‘D-Day’, you see a huge influx of thousands of people, each with their own devices, needing to connect to your network and your infrastructure. The floodgates are opened. But certain parts of your digital environment need to remain protected: your sensitive employee and customer data, your critical OT systems. I liken this to opening the door to your home, and letting the entire town come in and wander around. But you still need to secure your master bedroom.

A multitude of different actors must be able to work on-site to provide services or content during the event. Broadcasters, staff and suppliers need to have access to manage the show, and all these people need to access or interact with the IT infrastructure. In many ways, these additional bodies are already inside the perimeter and could host unknown malicious threats.

This year, the paradox is wider than ever. A tournament spread across hundreds of suppliers and vendors means the foothold an attacker needs may already belong to a trusted partner – a single compromised supplier can become the doorway to everything else. And the adversary is no longer working alone: generative AI now lets attackers probe and weaponize vulnerabilities across thousands of software dependencies at a speed no human team could match, turning the access paradox from a manageable risk into a fast-moving target.

Achieving this balance between accessibility and security requires a shift in mindset from perimeter-based security to one that can detect and respond to threats on the inside. The complexities involved requires technology that can identify malicious behavior in real time based on the wider context of an incident. A particular behavior or connection may be benign in one context and yet critically disruptive in another — tools and technology must be able to discern between the two.

This is why I considered Darktrace’s Self-Learning AI a suitable fit: rather than defending at the perimeter, it focuses on detecting and responding to malicious activity already inside. Because it learns the unique ‘patterns of life’ of its surroundings, it can detect subtle deviations that indicate a threat and initiate a targeted response – without relying on pre-programmed rules and playbooks.

IT/OT convergence

The second key challenge is the issue of IT and OT convergence. Typical stadiums and arenas consist of a wide range of Industrial Control Systems (ICS).

This involves a complex and messy array of switches, cables, CCTV cameras, as well as devices and technologies being brought in by the media and the press, and all these IT and OT components are now interconnected, which means these technologies now have Internet Protocol (IP)-based threats to manage. The same challenges that the corporate infrastructure for stadium management faces in cyber security are therefore also now an issue for ICS security.

This challenge cannot be addressed by viewing IT and OT security in isolation — these two environments are linked because of the analogue migration to IP. A unified approach is required to detect and respond to threats that start in IT before moving to industrial systems.

The stakes are physical. CCTV, Access Control, Public Annoucement system, lighting and the giant screens are all now running over IP, and a disruption to any of them can force a venue to halt play on safety grounds. Scale compounds the problem. At the Qatar 2022 World Cup, eight stadiums were purpose-built to a single technical standard, which made the digital environment relatively uniform to defend. The 2026 tournament is the opposite: dozens of host venues across three countries, each with its own operator, its own contractors and its own legacy systems.This creates a far more fragmented and unpredictable estate to secure.

In addition, cyber security technology must be able to deal with complexity. Darktrace’s AI thrives in the most complex environments, with more data points adding more context to inform the AI’s decision making. It covers OT and IT with a single, unified AI engine, that can also detect and respond across cloud infrastructure, SaaS applications, email systems and endpoints. It is ready to adapt to the messy, interconnected systems that make up large stadiums’ digital infrastructure.

The time factor

Finally, the nature of stadium events means that timing is critical and puts enormous pressure on the organizers and operators. ‘D-Day’ cannot be replayed or postponed, and so if cyber disruption occurs during the event, every minute is crucial. You cannot reschedule a World Cup final or move an opening ceremony; the date is fixed, the world is watching, and there is no second take.

There is consequently a strong emphasis on two key metrics

  • Mean Time To Know (MTTK) — how long it takes the security team need to be aware of an incident; and
  • Mean Time To Restore (MTTR) — how quickly a team can act to contain the threat.

It is perhaps more imperative in stadium event management than anywhere else that these two metrics be minimized.

This leads to the third criteria in assessing cyber security technology: does it help with response? And critically, can that response be nuanced and targeted, able to contain that threat without causing further disruption?

To this end, Darktrace’s Autonomous Response takes machine-speed action to contain cyber-attacks, when humans are too slow to react or aren’t around at all. It’s powered by Darktrace’s AI, so it has a nuanced and continuously updating understanding of what’s ‘normal’ across IT and OT systems. This means its response actions are targeted: designed to eliminate the threat, but not at the cost of disruption. Crucially, this enables responses that are surgical rather than blunt. For example, taking an entire server offline to stop a ransomware attack can cause more disruption than the attack itself, so the real value lies in neutralizing the malicious activity precisely — containing the threat without taking down the systems the event and business depends on.

Depending on the nature and severity of the threat, the technology can block specific malicious connections by enforcing the normal ‘pattern of life’ of a device or account. When every second counts, this is the speed and granularity that you need in a cybersecurity technology.

Darktrace can be deployed across every area of the digital enterprise, including network, email, cloud and SaaS environments with the same self-learning approach, stopping anomalous behaviors that point to account takeover and other cloud-based threats. Earlier this year, we announced that Darktrace is also extending its behavioral approach to help businesses deploy and scale AI securely by understanding how these AI systems and agents behave, interact with other systems and humans, and evolve over time. This is critical because 72% of cybersecurity professionals at sports organizations believe AI will increase their cyber risk over the next 12 months [2].

Wherever it is deployed, Darktrace allows the stadium operator to focus on the vital part of the game and offers real-time protection without any modification in the network topology or infrastructure.

An adaptive defense

Cyber-criminals are constantly developing their approach in an attempt to evade security tools trained to look for specific hallmarks of an attack. As they get creative and continuously experiment with new tactics and techniques, the human operators using these tools are forced into a constant state of catch up.

An AI-based approach that learns an organization and its normal behavior patterns from the ground up puts an end to this game of ‘cat and mouse’, shifting the balance in favor of the defenders and allowing them to stay ahead of the threat. This matters more than ever, because adversaries are now using AI to scale their attacks. If you do not have AI working to protect you against malicious AI, you are already at a disadvantage.

With a nuanced understanding of what’s ‘normal’ for the business, unified IT/OT coverage, and an Autonomous Response solution that takes immediate, surgical action, the playing field is leveled, and large stadium and events operators can focus on delivering the best possible experience for attendees, digital viewers, partners and performers.

References:

[1] [2] Darktrace: Cybersecurity in Global Sport, June 2026. Findings based on survey of 875 IT cybersecurity professionals based in the US, UK, Australia and Germany, working in professional sports organizations (including clubs, societies & sporting bodies) employing 10+ people. The survey was fielded between May 28, 2026 and June 3, 2026 by independent market research agency, Opinion Matters.

Continue reading
About the author
Your data. Our AI.
Elevate your network security with Darktrace AI