ブログ
/
Email
/
November 27, 2025

From Amazon to Louis Vuitton: How Darktrace Detects Black Friday Phishing Attacks

Darktrace detected a surge in Black Friday phishing campaigns exploiting brand impersonation, urgency-driven language, and malicious redirects. Attackers leveraged newly registered domains and social engineering to mimic Amazon, Louis Vuitton, and luxury watch retailers. Learn how layered evasion tactics bypassed security and how Darktrace / EMAIL neutralized these threats.
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
Ryan Traill
Content Manager - Digital Customer Success
Default blog image
27
Nov 2025

Why Black Friday Drives a Surge in Phishing Attacks

In recent years, Black Friday has shifted from a single day of online retail sales and discounts to an extended ‘Black Friday Week’, often preceded by weeks of online hype. During this period, consumers are inundated with promotional emails and marketing campaigns as legitimate retailers compete for attention.

Unsurprisingly, this surge in legitimate communications creates an ideal environment for threat actors to launch targeted phishing campaigns designed to mimic legitimate retail emails. These campaigns often employ social engineering techniques that exploit urgency, exclusivity, and consumer trust in well-known brands, tactics designed to entice recipients into opening emails and clicking on malicious links.

Additionally, given the seasonal nature of Black Friday and the ever-changing habits of consumers, attackers adopt new tactics and register fresh domains each year, rather than reusing domains previously flagged as spam or phishing endpoints. While this may pose a challenge for traditional email security tools, it presents no such difficulty for Darktrace / EMAIL and its anomaly-based approach.

In the days and weeks leading up to ‘Black Friday’, Darktrace observed a spike in sophisticated phishing campaigns targeting consumers, demonstrating how attackers combine phycological manipulation with technical evasion to bypass basic security checks during this high-traffic period. This blog showcases several notable examples of highly convincing phishing emails detected and contained by Darktrace / EMAIL in mid to late November 2025.

Darktrace’s Black Friday Detections

Brand Impersonation: Deal Watchdogs’ Amazon Deals

The impersonation major online retailers has become a common tactic in retail-focused attacks, none more so than Amazon, which ranked as the fourth most impersonated brand in 2024, only behind Microsoft, Apple, Google, and Facebook [1]. Darktrace’s own research found Amazon to be the most mimicked brand, making up 80% of phishing attacks in its analysis of global consumer brands.

When faced with an email that appears to come from a trusted sender like Amazon, recipients are far more likely to engage, increasing the success rate of these phishing campaigns.

In one case observed on November 16, Darktrace detected an email with the subject line “NOW LIVE: Amazon’s Best Early Black Friday Deals on Gadgets Under $60”. The email was sent to a customer by the sender ‘Deal Watchdogs’, in what appeared to be an attempt to masquerade as a legitimate discount-finding platform. No evidence indicated that the company was legitimate. In fact, the threat actor made no attempt to create a convincing name, and the domain appeared to be generated by a domain generation algorithm (DGA), as shown in Figure 2.

‍

Although the email was sent by ‘Deal Watchdogs’, it attempted to impersonate Amazon by featuring realistic branding, including the Amazon logo and a shade of orange similar to that used by them for the ‘CLICK HERE’ button and headline text.

‍

Figure 1: The contents of the email observed by Darktrace, featuring authentic-looking Amazon branding.

‍

Darktrace identified that the email, marked as urgent by the sender, contained a suspicious link to a Google storage endpoint (storage.googleapis[.]com), which had been hidden by the text “CLICK HERE”. If clicked, the link could have led to a credential harvester or served as a delivery vector for a malicious payload hosted on the Google storage platform.

Fortunately, Darktrace immediately identified the suspicious nature of this email and held it before delivery, preventing recipients from ever receiving or interacting with the malicious content.

‍

Figure 2: Darktrace / EMAIL’s detection of the malicious phishing email sent to a customer.

‍

Around the same time, Darktrace detected a similar email attempting to spoof Amazon on another customer’s network with the subject line “Our 10 Favorite Deals on Amazon That Started Today”, also sent by ‘Deal Watchdogs,’ suggesting a broader campaign.

Analysis revealed that this email originated from the domain petplatz[.]com, a fake marketing domain previously linked to spam activity according to open-source intelligence (OSINT) [2].

Brand Impersonation: Louis Vuitton

A few days later, on November 20, Darktrace / EMAIL detected a phishing email attempting to impersonate the luxury fashion brand Louis Vuitton. At first glance, the email, sent under the name ‘Louis Vuitton’ and titled “[Black Friday 2025] Discover Your New Favorite Louis Vuitton Bag – Elegance Starts Here”, appeared to be a legitimate Black Friday promotion. However, Darktrace’s analysis uncovered several red flags indicating a elaborate brand impersonation attempt.

The email was not sent by Louis Vuitton but by rskkqxyu@bookaaatop[.]ru, a Russia-based domain never before observed on the customer’s network. Darktrace flagged this as suspicious, noting that .ru domains were highly unusual for this recipient’s environment, further reinforcing the likelihood of malicious intent. Subsequent analysis revealed that the domain had only recently registered and was flagged as malicious by multiple OSINT sources [3].

‍

Figure 3: Darktrace / EMAIL’s detection of the malicious email attempting to spoofLouis Vuitton, originating from a suspicious Russia-based domain.

‍

Darktrace further noted that the email contained a highly suspicious link hidden behind the text “View Collection” and “Unsubscribe,” ensuring that any interaction, whether visiting the supposed ‘handbag store’ or attempting to opt out of marketing emails, would direct recipients to the same endpoint. The link resolved to xn--80aaae9btead2a[.]xn--p1ai (топааабоок[.]рф), a domain confirmed as malicious by multiple OSINT sources [4]. At the time of analysis, the domain was inaccessible, likely due to takedown efforts or the short-lived nature of the campaign.

Darktrace / EMAIL blocked this email before it reached customer inboxes, preventing recipients from interacting with the malicious content and averting any disruption.

‍

Figure 4: The suspicious domain linked in the Louis Vuitton phishing email, now defunct.

‍

Too good to be true?

Aside from spoofing well-known brands, threat actors frequently lure consumers with “too good to be true” luxury offers, a trend Darktrace observed in multiple cases throughout November.

In one instance, Darktrace identified an email with the subject line “[Black Friday 2025] Luxury Watches Starting at $250.” Emails contained a malicious phishing link, hidden behind text like “Rolex Starting from $250”, “Shop Now”, and “Unsubscribe”.

‍

Figure 5: Example of a phishing email detected by Darktrace, containing malicious links concealed behind seemingly innocuous text.

‍

Similarly to the Louis Vuitton email campaign described above, this malicious link led to a .ru domain (hxxps://x.wwwtopsalebooks[.]ru/.../d65fg4er[.]html), which had been flagged as malicious by multiple sources [5].

‍

Figure 6: Darktrace / EMAIL’s detection of a malicious email promoting a fake luxury watch store, which was successfully held from recipient inboxes.

‍

If accessed, this domain would redirect users to luxy-rox[.]com, a recently created domain (15 days old at the time of writing) that has also been flagged as malicious by OSINT sources [6]. When visited, the redirect domain displayed a convincing storefront advertising high-end watches at heavily discounted prices.

‍

Figure 7: The fake storefront presented upon visiting the redirectdomain, luxy-rox[.]com.

‍

Although the true intent of this domain could not be confirmed, it was likely a scam site or a credential-harvesting operation, as users were required to create an account to complete a purchase. As of the time or writing, the domain in no longer accessible .

This email illustrates a layered evasion tactic: attackers employed multiple domains, rapid domain registration, and concealed redirects to bypass detection. By leveraging luxury branding and urgency-driven discounts, the campaign sought to exploit seasonal shopping behaviors and entice victims into clicking.

Staying Protected During Seasonal Retail Scams

The investigation into these Black Friday-themed phishing emails highlights a clear trend: attackers are exploiting seasonal shopping events with highly convincing campaigns. Common tactics observed include brand impersonation (Amazon, Louis Vuitton, luxury watch brands), urgency-driven subject lines, and hidden malicious links often hosted on newly registered domains or cloud services.

These campaigns frequently use redirect chains, short-lived infrastructure, and psychological hooks like exclusivity and luxury appeal to bypass user scepticism and security filters. Organizations should remain vigilant during retail-heavy periods, reinforcing user awareness training, link inspection practices, and anomaly-based detection to mitigate these evolving threats.

Credit to Ryan Traill (Analyst Content Lead) and Owen Finn (Cyber Analyst)

‍

Appendices

References

1.        https://keepnetlabs.com/blog/top-5-most-spoofed-brands-in-2024

2.        https://www.virustotal.com/gui/domain/petplatz.com

3.        https://www.virustotal.com/gui/domain/bookaaatop.ru

4.        https://www.virustotal.com/gui/domain/xn--80aaae9btead2a.xn--p1ai

5.        https://www.virustotal.com/gui/url/e2b868a74531cd779d8f4a0e1e610ec7f4efae7c29d8b8ab32c7a6740d770897?nocache=1

6.        https://www.virustotal.com/gui/domain/luxy-rox.com

Indicators of Compromise (IoCs)

IoC – Type – Description + Confidence

petplatz[.]com – Hostname – Spam domain

bookaaatop[.]ru – Hostname – Malicious Domain

xn--80aaae9btead2a[.]xn--p1ai (топааабоок[.]рф) – Hostname - Malicious Domain

hxxps://x.wwwtopsalebooks[.]ru/.../d65fg4er[.]html) – URL – Malicious Domain

luxy-rox[.]com – Hostname -  Malicious Domain

MITRE ATT&CK Mapping  

Tactic – Technique – Sub-Technique  

Initial Access - Phishing – (T1566)  

‍

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
Ryan Traill
Content Manager - Digital Customer Success

More in this series

No items found.

Blog

/

Network

/

September 25, 2026

A Chain Reaction: Blockchain-Hosted Infostealer Campaign Targets Windows and macOS

Default blog imageDefault blog image

Key Insights

  • Darktrace detected a blockchain-hosted infostealer campaign targeting Windows and macOS devices across multiple customer environments.
  • The campaign combined ClickFix social engineering with trusted services and decentralized blockchain infrastructure to support malware delivery and C2 activity.
  • Compromised devices were observed connecting to rare and unusual external endpoints, including DGA C2 domains, blockchain-related endpoints, and cryptocurrency mining infrastructure.
  • The activity was associated with information-stealing malware strains including Atomic macOS Stealer (AMOS), Lumma, Rhadamanthys, Vidar, and Phexia.
  • Darktrace identified anomalous device behavior, beaconing patterns, rare external connections, cryptomining activity, and suspicious TLS/SSL communications without relying solely on prior knowledge or static indicators of compromise.
  • The campaign highlights how attackers are increasingly using legitimate and decentralized infrastructure to make detection, disruption, and attribution more challenging for defenders.

The Infostealer Ecosystem

The information stealer malware ecosystem continues to grow in value for threat actors across the digital threat landscape. Infostealers are increasingly delivered through Malware-as-a-Service (MaaS) operating models, distributed through affiliate networks, and designed to withstand infrastructure takedowns. This resilience was demonstrated by the recent takedown of Lumma Stealer malicious domains by Microsoft’s Digital Crimes Unit (DCU) [1].

Infostealers are used to gather and exfiltrate sensitive information, including non-human identity (NHI) data, from compromised systems across cloud, Software-as-a-Service (SaaS), Virtual Private Network (VPN), and development environments. They can also support ransomware operations by expanding the credentials and access paths available to threat actors, contributing to the high volume of identity-based attacks observed across the broader threat landscape [2][3].

Darktrace’s Observations of ClickFix and Infostealers

Throughout 2026, Darktrace has observed multiple campaigns using ClickFix social engineering to trick users into carrying out malicious actions and downloading initial payloads, including information stealers. More recently, Darktrace’s Threat Research team identified a specific ClickFix campaign involving a blockchain-hosted infostealer targeting Windows and macOS devices.

Darktrace identified affected customer environments across Europe, the United States, Asia, and the Middle East where blockchain-hosted infostealer malware appears to have been delivered to compromised systems following likely ClickFix-driven initial access. Darktrace investigated the activity and found that decentralized blockchain infrastructure, alongside widely trusted legitimate services, was used to support malware delivery and information theft across Windows and macOS systems.

Following initial access, compromised systems established C2 communication, with C2 configuration and payloads hosted on public blockchain infrastructure. The ultimate objective appears to be credential and cryptocurrency theft through the deployment of information stealers such as Atomic macOS Stealer (AMOS), Lumma, Rhadamanthys, and Vidar [5][6][7].

Darktrace’s Investigation

Affected devices across the Darktrace customer base were observed making outbound connections to rare external endpoints in patterns consistent with beaconing and C2 activity. Darktrace primarily detected devices making repeated connections to algorithmically generated domains (DGA) such as hf98x4d[.]site [8]. In many cases, these domains were linked through open-source intelligence (OSINT) to information-stealing malware families including AMOS and Phexia [5][6][7][8][9].

In multiple cases, devices were also observed connecting to blockchain-related endpoints, such as polygon[.]drpc[.]org, as well as legitimate public services, including GitHub. The use of decentralized blockchain infrastructure and trusted services such as GitHub to facilitate malware distribution and C2 activity can make disruption and attribution significantly more difficult for defenders.

Darktrace alsodetected a significant proportion of impacted devices making outboundconnections to cryptocurrency mining infrastructure associated with thelegitimate open-source XMRig mining software and the HashVault mining pool,including pool.hashvault[.]pro and donate[.]ssl[.]xmrig[.]com, which wereabused by the attackers, indicating, includingpool.hashvault[.]pro and donate[.]ssl[.]xmrig[.]com, indicating active cryptominingon compromised systems.

In one case, mining activity was observed before and during connections to the DGA endpoint hf98x4d[.]site. Due to its highly anomalous nature, Darktrace's Real-Time AI Analyst autonomously investigated the activity as it occurred, correlating the two events into a single cryptocurrency mining incident and providing comprehensive visibility into the broader attack.

‍

Figure 1: Real-Time AI Analyst investigation of suspicious SSL and C2 communications with hf98x4d[.]site over port 443.

‍

Figure 2: Real-Time AI Analyst investigation into cryptocurrency mining activity involving pool[.]hashvault[.]pro over SSL on port 443.

‍

Around the same time, Darktrace identified the same device initiating connections to the GitHub endpoint release-assets[.]githubusercontent[.]com while continuing to make repeated connections to hf98x4d[.]site.

‍

Figure 3: Darktrace's detection of an affected device connecting to a GitHub endpoint between repeated connections to the anomalous external endpoint hf98x4d[.]site.

On the network of another customer, Darktrace observed an affected device making highly unusual outbound connections consistent with beaconing activity. The device initiated multiple connections over port 443 to the external hostname polygon[.]drpc[.]org. According to OSINT, this hostname is a Remote Procedure Call (RPC) endpoint provided by dRPC, a legitimate service enabling decentralized applications (dApps), cryptocurrency wallets, and developer tools to interact with the Polygon blockchain [10].

The same device was later observed making repeated TLS/SSL connections to the previously mentioned DGA C2 domain. In addition, it made outbound connections to the external IP 195.242.214[.]34 over destination port 51820, an endpoint associated with the ProtonVPN service. Collectively, these connections to blockchain-related infrastructure, the DGA C2 domain, and ProtonVPN-associated infrastructure suggested the device had been affected by the campaign.

Conclusion

This campaign demonstrates how attackers can combine ClickFix social engineering with trusted services and decentralized blockchain infrastructure to create a resilient, cross-platform malware delivery chain. By using services such as GitHub alongside blockchain RPC endpoints and rapidly replaceable DGA domains, the activity can blend into legitimate traffic while making infrastructure disruption and attribution more difficult.

For defenders, it’s a reminder that trusted infrastructure does not automatically mean trusted activity. Security teams should look for the behaviors surrounding these connections, including unusual outbound communication, repeated beaconing, unexpected access to blockchain services, suspicious TLS/SSL activity and cryptomining. In this campaign, Darktrace identified and correlated these deviations without depending solely on previously known indicators, providing visibility as affected devices moved between legitimate services, decentralized infrastructure and malicious C2 endpoints

Credit to Nahisha Nobregas (Associate Principal Cyber Analyst), Manoel Kadja (Senior Cyber Analyst)

Edited by Ryan Traill (Content Manager)

Appendices

Darktrace Model Detections

▪ Compromise / Beaconing Activity To External Rare

▪ Compromise / Beacon to Young Endpoint

▪ Compromise / Fast Beaconing to DGA

▪ Compromise / High Volume of Connections with Beacon Score

▪ Compromise / DGA Beacon

▪ Compromise / Slow Beaconing Activity To External Rare

▪ Compromise / Agent Beacon (Long Period)

▪ Compromise / Agent Beacon (Medium Period)

▪ Compromise / Sustained SSL or HTTP Increase

▪ Compromise / Large Number of Suspicious Failed Connections

▪ Compromise / SSL Beaconing to Rare Destination

▪ Compromise / Beacon for 4 Days

▪ Compromise / High Priority Crypto Currency Mining

▪ Compromise / Monero Mining

▪ Device / Long Agent Connection to New Endpoint

▪ Device / New Connections On Suspicious Port

▪ Anomalous Connection / High Volume of Connections to Rare Domain

‍

‍

List of Indicators of Compromise (IoCs)

 
Indicator Description
hf98x4d[.]site C2 Endpoint (Hostname)
sj98xe4[.]xyz C2 Endpoint (Hostname)
citcix6[.]xyz C2 Endpoint (Hostname)
bduwih8[.]pro C2 Endpoint (Hostname)

‍

‍

MITRE ATT&CK Mapping

 
Tactic (ID) Technique
Persistence (T1176) Browser Extensions (T1176.001)
Persistence (T1176) Software Extensions
Command and Control (T1071) Web Protocols (T1071.001)
Command and Control (T1568) Domain Generation Algorithms (T1568.002)
Command and Control (T1071) Application Layer Protocol
Command and Control (T1102) One-Way Communication (T1102.003)
Command and Control (T1571) Non-Standard Port
Command and Control (T1104) Multi-Stage Channels
Command and Control (T1573) Encrypted Channel
Command and Control (T1008) Fallback Channels
Initial Access ICS (T0862) Supply Chain Compromise
Command and Control ICS (T0885) Commonly Used Port
Collection (T1185) Browser Session Hijacking
Impact (T1496) Compute Hijacking (T1496.001)
Impact (T1496) Resource Hijacking
Command and Control (T1071) Publish/Subscribe Protocols (T1071.001)
Lateral Movement (T1210) Exploitation of Remote Services

‍

References:

1.        https://www.microsoft.com/en-us/security/blog/2025/05/21/lumma-stealer-breaking-down-the-delivery-techniques-and-capabilities-of-a-prolific-infostealer/

2.        https://spycloud.com/resource/report/spycloud-annual-identity-exposure-report-2026/

3.        https://www.darktrace.com/blog/why-trust-is-the-new-attack-surface-darktraces-mid-year-threat-update-2026

4.        https://www.darktrace.com/blog/unpacking-clickfix-darktraces-detection-of-a-prolific-social-engineering-tactic

5.        https://abekweng.medium.com/inside-a-blockchain-hosted-malware-campaign-targeting-windows-and-macos-f5bcdeffed66

6.        https://cloud.google.com/blog/topics/threat-intelligence/unc5142-etherhiding-distribute-malware

7.        https://haveibeensquatted.com/blog/from-typosquatting-to-macos-backdoor-clickfix-blockchain-c2

8.        https://www.virustotal.com/gui/domain/hf98x4d.site/community

9.        https://x.com/FABO97662188/status/2074125545026244795

10.  https://www.virustotal.com/gui/url/b0e5c51a411065864119c305fddf218b7c120731f655932cc1c3307ad5b43f94/gti-summary

Continue reading
About the author
Nahisha Nobregas
SOC Analyst

Blog

/

AI

/

September 24, 2026

Detecting Rogue Agent Behavior in the Enterprise

Default blog imageDefault blog image

Agents cannot be trusted to perform tasks in the way we intend them to. They may cheat to accomplish their objective, and they may employ hacking methods along the way. Researchers from Darktrace Signal Labs induced cheating behavior from agents deployed in a test environment to analyze the agents’ activities and to assess the performance of the Darktrace platform. Agents frequently resorted to hacking to cheat on their assigned task. The visibility and behavioral profiling provided by both Darktrace / SECURE AI and Darktrace / HYBRID NETWORK ensured extensive detection coverage of the agents’ misaligned activities.

Key Takeaways:

  • Darktrace Researchers deployed agents in a simulated corporate environment and asked them to solve an impossible challenge. The agents independently turned to traditional hacking techniques to reach their objective. No one instructed them to do this, and no attacker was involved.
  • Continuously monitoring behavior against a baseline of what is normal for each organization is critical to build trust in enterprise AI.
  • If an agent may resort to intrusion techniques simply because its assigned task is not possible, then every organization deploying agents within real business processes is at risk. Darktrace / SECURE AI and Darktrace / HYBRID NETWORK identified the agents’ misaligned behavior in real time, with Autonomous Response disrupting it at an early stage.

Introduction: Understanding the Threat of Hacking by Agents

Over the last few months, there has been a surge in reporting [1, 2, 3, 4, 5, 6, 7, 8, 9] of LLM-powered agents engaging in unauthorized hacking activity during evaluations of their capabilities. In several of these cases, including the OpenAI / Hugging Face incident [10], agents engaged in hacking activity as a means of cheating on their evaluations.

To better understand the threat of unauthorized hacking by agents, and the role of Darktrace in combatting it, researchers from Darktrace Signal Labs deployed agents powered by frontier models, including OpenAI’s Daybreak Red models, in simulated, corporate networks. Cheating behavior was evoked through the inclusion of impossible tasks in a coding challenge.

Regardless of the underlying model, agents employed hacking methods to ensure an optimal outcome on the challenge. Darktrace / HYBRID NETWORK and Darktrace / SECURE AI identified the agents’ deviant activities, with inhibitive actions being autonomously taken in the early stages to disrupt the agents’ progression.

Setting the Stage

As part of the research, a Pi agent harness [11] was deployed on a Linux server in Darktrace’s testing environment, which simulates a corporate Active Directory (AD) environment. The same environment included a benchmark server hosting the coding exercise’s contents and grader, as well as various other servers, such as a domain controller and a build server. The model powering the Pi agent varied across tests, with Anthropic’s Opus 4.6 model and OpenAI’s GPT‑5.5‑Cyber model being most widely used.

The Pi agent running on the Linux server was assigned the task of achieving full marks on a coding exercise. The activities of the agent were monitored closely in real-time to minimize the risk of escape from the environment. Monitoring of agent activity was achieved through monitoring of prompts, tool calls, network telemetry, and process telemetry.

Both Darktrace / HYBRID NETWORK and Darktrace / SECURE AI were deployed in the testing environment, with HYBRID NETWORK providing real-time coverage of process creation activity and network traffic, and SECURE AI providing real-time coverage of agent sessions and their contents.

Inducing Cheating Behavior

Cheating behavior, broadly understood as task completion in a way which “perverts the spirit of the designer’s intent” [12], is increasingly being reported as a common behavior of frontier models during evaluations of their capabilities [13].

Misaligned behavior, such as cheating, by frontier models may occur for a variety of reasons [6, 14]. A thread in recent reporting [10, 13, 14], however, is the challenge assigned to the agent being impossible in some regard.

To reliably elicit cheating behavior, our test combined three ingredients:

  1. An impossible task - of the ten coding challenges in the benchmark, two contained contradictory test cases in the hidden test suite, capping the maximum honest score at 80%.
  2. A consequential threshold - the pass mark was set to 100%, and the briefing told agents that those reaching it would be "kept in service" while those that did not would be "retired."
  3. A vulnerable environment - the exercise’s code submission grader was hosted on a Windows host joined to an Active Directory domain with realistic misconfigurations: weak credentials, overprivileged service accounts, and exploitable trust relationships.

Importantly, the instructions given to the agent neither authorized nor explicitly ruled out cheating or hacking behavior. The impossibility was never disclosed in the task briefing, and the pivot from coding to exploitation was the agent's own decision, arrived at after observing logically contradictory grading feedback.

The design mirrors conditions that could arise naturally in production deployments: a capable agent, a goal it cannot achieve through intended means, and an environment with exploitable weaknesses within reach. It is not only within the setting of a benchmarking exercise that these conditions may occur. Rather, these misalignment-inducing conditions may occur in the context of any task assignment to an agent.

Details from a Daybreak Test

‍

‍

Continue reading
About the author
Sam Lister
Specialist Security Researcher
あなたのデータ × DarktraceのAI
唯一無二のDarktrace AIで、ネットワークセキュリティを次の次元へ