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 Exploits & Zero-Days
Mobile Apps Expose Billions of Unencrypted User Info Through Insecure SDKs

Android mobile apps reusing advertising SDKs still using HTTP protocol risk exposing unencrypted user personal information, security researchers warned at the RSA Conference.

Read Article
Vulnerabilities in Banking-Related Web Applications Highlight Significance of Secure DevOps

An audit of source codes in certain web applications found that 85 percent contained vulnerabilities, with finance and banking-related web applications the most susceptible.

Read Article
Exploits & Zero-Days OT & critical infrastructure
DoS, Injection Flaws Among Vulnerabilities Found in ICS, SCADA Routers

Security researchers reported several vulnerabilities in ICS routers commonly used in vital infrastructures, such as water and electricity generation and distribution.

Read Article
Securing IP Surveillance Cameras in the IoT Ecosystem

We discuss how manufacturers, users, and other involved parties can prevent IoT security incidents and work toward securing surveillance cameras in the market.

Read Article
Data privacy & regulation
Securing Data Through GDPR’s Privacy by Design

Privacy by Design is a concept that businesses should adopt as they modernize their operations, especially in this data-driven world.

Read Article
Naming the Unknown: Labeling Unknown Files Through Machine Learning

Because most malware threats come from software download events, Trend Micro subsequently developed a human-readable machine learning system that successfully classifies unknown files into either benign or malicious in nature.

Read Article
Data privacy & regulation
ICANN’s WhoIs a GDPR Compliance Challenge

ICANN focuses on preserving its WhoIs protocol as it continues to develop interim models for GDPR compliance.

Read Article
Malware Cyber crime
No Macros Required: Design in RTF and Vulnerability in Office Exploited to Deliver Formbook RAT

Security researchers uncovered a multi-stage attack chain that takes advantage of a design behavior in RTF files and a vulnerability in Microsoft Office (CVE-2017-8570) to deliver the Formbook RAT.

Read Article
Threats to Voice-Based IoT and IIoT Devices

With plenty of voice-based internet-of-things devices in use around the world, it is expected that they will become riddled with compatibility issues and privacy concerns. What threats are there and what can be done to mitigate them?

Read Article
Data privacy & regulation Cyber risk
Balancing Security and Public Interest: The GDPR and the Public Sector

The European Union’s General Data Protection Regulation (GDPR) will be enforced in May of this year. We dive into how this wide-ranging regulation affects organizations acting in the public interest. The GDPR recognizes that there must be some leeway given in

Read Article