Skip to main content

TrendAI™ 深度研究

spark

Featured Articles

Seven Principles Behind the Adoption of AI in Cybercrime
AI

AI 網路犯罪七大運作原則:為何駭客追求規模化,而非全自動攻擊

AI 尚未催生全新的網路犯罪模式,卻正讓既有犯罪手法變得更快速、成本更低,也更容易規模化。 趨勢科技 TrendAI™ 最新研究歸納出網路犯罪者採用 AI 的七大原則,解析 AI 如何提升網路釣魚與詐騙活動的執行效率、加速被竊資料的分析與處理,並逐步應用於惡意程式開發。同時指出,AI 代理程式雖已被用於實際入侵,但其自主攻擊能力仍受到技術可靠性、基礎設施存取權及人為監督等條件限制。

Read article
Beyond Ransomware: Tracking the Underground Trade in Law Firm Access and Data
Cybercriminal underground
不只勒索軟體:法律事務所存取權限與機密資料遭地下市場反覆轉售

法律事務所的資安風險,未必會隨勒索軟體攻擊結束而消失。趨勢科技 TrendAI™ 研究團隊發現,網路犯罪者會在地下市場反覆兜售法律事務所的系統存取權限與機密資料,部分交易甚至在資安事件公開前就已出現,事件結案後仍持續流通。研究顯示,公開的勒索軟體資料外洩紀錄,可能只是法律產業所面臨資安威脅的一部分。

Mayra Rosario Fuentes
Read article
AI governance AI
AI 代理程式(AI Agent)資安風險與防護:NVIDIA OpenShell 與 TrendAI Vision One™ 實測解析

AI 代理程式(AI Agent)不只是聊天機器人,更能自主規劃與執行任務、呼叫外部工具,甚至與其他 AI 代理程式協作。隨著自主性提高,企業也面臨提示詞注入攻擊(Prompt Injection)、權限過大及機密資訊外洩等資安風險。 趨勢科技 TrendAI™ 透過實際測試,探討如何結合 NVIDIA OpenShell 與 TrendAI Vision One™,運用最小權限原則及涵蓋預防、偵測與應變的多層安全控管機制,協助企業降低 AI 代理程式帶來的資安風險,強化安全治理。

Naonari Tanimoto (Solutions Architect Specialist, Trend AI), Writing Support: Omi Tokunaga (Solutions Architect, NVIDIA G.K.)
Read article
The Browser Is Now an AI Runtime: Security Risks in Chrome's On-Device Models
Cyber risk AI
Google Chrome 內建 AI 模型的三類資安風險:提示詞注入、運算資源濫用與工具呼叫攻擊

Google Chrome 會在符合條件的桌面裝置上自動下載約 4.27 GB 的 Gemini Nano 語言模型,使瀏覽器成為裝置端 AI 執行環境。然而,在現行架構下,任何 HTTPS 網站都能在沒有使用者同意提示、使用狀態指示及速率限制的情況下,於背景呼叫該模型,衍生提示詞注入(Prompt Injection)、運算資源濫用(Parasitic Computing),以及實驗性工具呼叫功能所涉及的潛在 Return-to-Tool(RTT)攻擊風險。 本文深入解析這三類資安風險,並提供企業資安團隊與開發者具體的防護及治理建議。

Kirill Gelfand, Vladimir Kropotov, Fyodor Yarochkin, David Tulis
Read article
IoT & smart devices
High-Tech Highways

Intelligent Transportation Systems are slowly being adopted all over the world. Securing the future of transportation from cyberattacks should be a top priority.

Read Article
Cybercriminal underground
The Middle Eastern and North African Underground: Where Culture and Cybercrime Meet

The Middle Eastern and North African (MENA) underground is characterized by its ironic mix of ideology and felony. We take a look at its inner workings, available wares, and the unique sense of brotherhood shared by its players.

Read Article
Phishing & BEC
Spam, BEC, Ransomware: The Continuing Abuse of Email by Old and New Threats

The scope of attacks and the rampant rate with which the abuse of email managed to inflict on businesses and users points to the effectiveness of email-borne threats.

Read Article
Cloud security
Verizon’s Internal Data Exposed on Unprotected AWS Server

Misconfigured cloud servers continue to be a problem. As cloud services are rapidly gaining ground globally and across all industries, many organizations adopt the technology without fully securing it.

Read Article
Cyber crime Malware
A Shift in the ATM Malware Landscape: From Physical to Network-based Attacks

ATM malware has become a mainstay in many cybercriminals’ arsenal due to its capability to steal money. In our joint efforts with Europol’s EC3, we explain in detail how criminals continue to leverage different ATM malware families and attack types.

Read Article
Cyber crime Phishing & BEC
What do Hackers do with Your Stolen Identity?

Identity theft is currently a gold mine for cybercriminals—one that reached an all-time high in 2016, with up to $16 billion worth of losses caused by fraud and identity theft. But what exactly happens with the stolen information?

Read Article
Cyber crime Cyber propaganda
Fake News and Cyber Propaganda: The Use and Abuse of Social Media

This research paper explores the tools and methods used to spread fake news and manipulate public opinion: the services that enable them, their appearance on social media sites, and the motivations behind these activities.

Read Article
Exploits & Zero-Days
Securing Smart Cities

Cities around the world are getting smarter, but are they being designed with security in mind?

Read Article
Exploits & Zero-Days
The State of SCADA HMI Vulnerabilities

A complete discussion of the different vulnerability categories, including case studies of vulnerable SCADA HMIs. The paper also provides a guide for vulnerability researchers, as well as vendors on quick and efficient bug discovery.

Read Article
IoT & smart devices Botnets
Protecting Home Networks: Start by Securing the Router

As home routers add more features, securing them becomes more difficult. End users should be aware of the effects of compromise, and how to protect their home routers.

Read Article