Avatar of TonTon H.-D. Huang.
TonTon H.-D. Huang
Senior Technical Architect
ProfilePortfolio
Posts
0Connections
Print
Avatar of the user.

TonTon H.-D. Huang

Senior Technical Architect
黃 獻 德(Hsien-De Huang, also known as TonTon), is a seasoned professional with over a decade of expertise in the field of Artificial Intelligence. His extensive skill set encompasses image recognition, natural language processing, speech processing, and cyber-security, with a focus on specializing in x86/Android malware analysis. His career has been marked by the presentation of numerous research papers and patent applications at international cybersecurity conferences, including Defcon, OWASP AppSec USA, RuxCon, and HITCON. Apart from work, he received the Ph.D. degree in Computer Science and Information Engineering from the National Cheng Kung University. His doctoral thesis is titled "Deep Learning-based Anomaly Analysis in Cyber Threats,". He is also the founder of Taiwan's pioneering artificial intelligence meetup, Deep Learning 101, and the Taiwan AI Group, dedicated to propelling innovation and knowledge-sharing in these exciting fields.
Information Communications
Logo of the organization.
國立成功大學 National Cheng Kung University
Taipei City, 台灣

Professional Background

  • Current status
  • Profession
    Research / R&D
  • Fields
    Computer Networking
  • Work experience
    10-15 years (6-10 years relevant)
  • Management
    I've had experience in managing 5-10 people
  • Skills
    Cyber Security
    AI & Machine Learning
  • Languages
    English
    Intermediate
  • Highest level of education
    Doctoral

Job search preferences

  • Desired job type
    Full-time
    Interested in working remotely
  • Desired positions
    Software Engineer, Research & Development, Project Manager
  • Desired work locations
    Taipei City, Taiwan
  • Freelance
    Non-freelancer

Work Experience

Manager, Department Chief, (AI/CyberSecurity)

Dec 2023 - Present
Taipei City, Taiwan
Big Data Analytics Dep., Data Analytics Technology Div. 與部門同仁共同專注發展人工智慧及網路安全之應用於集團資料分析、客戶經驗及專案管理等資訊系統規劃、開發及維運,包含機器學習、深度學習、資料科學等。
Logo of the organization.

Senior Technical Architect (AI)

Jul 2022 - Dec 2023
1 yr 6 mos
Taipei City, Taiwan
應用命名實體識別和事件擷取,針對醫療診斷書的醫囑分析,開發其醫療類別和相關起迄日等資訊;提升登打人員驗證相關表單效率。 https://blog.twman.org/2023/07/HugIE.html Applying named entity recognition and event extraction, analyze medical diagnostic reports to develop medical categories and related start and end dates, enhancing the efficiency of verifying relevant forms by data entry personnel. https://github.com/Deep-Learning-101/CathayIE 針對醫療診斷書和收據用 PaddleOCR 做光學字元辨識技術採用文本偵測、文本識別及關鍵資訊擷取做分析,開發其表單資訊分析;提升登打人員驗證相關表單效率。 For medical diagnosis reports and receipts, PaddleOCR is utilized for optical character recognition (OCR) technology. This involves text detection, text recognition, and key information extraction for analysis, enabling the development of form information analysis. This enhances the efficiency of data entry personnel in verifying relevant forms. 應用語音識別和語音去噪,針對遠距投保/電話訪問/客服等語音,預期開發其相關、語音文字質檢用,提升質檢人員驗證話術驗證之效率。 Applying speech recognition and noise reduction, develop related speech-to-text quality assurance tools for remote insurance applications, telephone interviews, and customer service, enhancing the efficiency of verifying language proficiency by quality assurance personnel. 應用聲紋識別,針對壽險客服之聲紋驗證,預期開發相關語音和聲紋等相關檢測,降低保戶與業務被造假之問題。 Applying voiceprint recognition, develop related voice and voiceprint detection tools for life insurance customer service voiceprint verification, reducing the problem of policyholders and agents committing fraud.
Logo of the organization.

Senior Technical Expert and Team Lead

Leopard Mobile
Full-time
Dec 2015 - Mar 2021
5 yrs 4 mos
Taipei City, Taiwan
Developed the State-Of-The-Art algorithms and designed the architecture to fulfill the product's requirements. Design architecture, generate our own datasets, model quantization, and enhance performance (including improving response time to milliseconds, model size, precision and accuracy). Concerning speech separation, enhancement, speaker recognition, and speech recognition, which improve the quality of voice, integrate with name entity recognition, classification, similarity, correction, and machine reading comprehension, and improve the user experience to make the robots understand the human meaning. Cyber-security: focused on malware, blockchain vulnerability analysis and cryptocurrency ranking Presented at Defcon, RuxCon, OWASP Appsec, HITCON and Career: Machine Learning Expert. (link) AI: Speech Processing, Natural Language Processing, and Computer Vision. Defending Taiwan, Fighting the Pandemic with Technology. (link) NVIDIA Developer: AI Improves the Frequency and Quality of Mobile App Notifications (link). 規劃設計及建置公司機器學習(ML)/深度學習(DL)之產品架構的演算法模型、需求分析、技術流程 (含AutoML與MLOps),研發品質與版本控管及發展輪廓和藍圖 開發服務型機器人、AI智能助理、惡意廣告與騷擾電話識別等圖像、自然語言處理及語音處理等機器學習(ML)/深度學習(DL)之產品 Career - 十大熱門人才系列報導: 機器學習專家 科技抗疫: 提高聲紋辨識正確率,添防疫新利器 Android 及區塊鏈威脅分析(R2-D2)、加密貨幣分析和App廣告彈窗推薦系統(C-3PO) Defcon, RuxCon, OWASP Appsec, HITCON https://www.twman.org/research/R2D2 https://www.twman.org/research/C3PO 語音訊號處理:建置提升服務型機器人的語音互動體驗API服務。 https://www.twman.org/AI/ASR 聲紋識別:藉開源aishell數據,整合SincNet模型及Kaldi,優化模型與數據集,提供API容器,提升聲紋辨識準確度從0.88提升至0.94,用於家用型服務機器人;報導於國網中心科技抗疫。 https://www.twman.org/AI/ASR/SpeakerRecognition 語音去噪:藉由aishell以及ESC-50和FSDnoisy18k等開源語音數據,以FACEBOOK的denoiser和DEMUCS為模型基礎,針對其中的TasNet及Conv-TasNet做優化(包含串流及多通道),提升STOI並將模型由73.4MB量化至9MB,CPU推論API由0.2秒加速至0.08秒。 https://www.twman.org/AI/ASR/SpeechEnhancement 語音分割:優化需要透過中間狀態傳遞資訊的RNN/CNN模型的分離效果,並整合sudo-rm自監督模型採multi-resoultion feature 的下採樣與重採樣,使用depth-wise convolutions於wsj0-2mix數據優化,並新增修正各種語音重疊長度,模型由11MB量化至3MB,CPU推論API由2.4秒加速至0.27秒。 https://www.twman.org/AI/ASR/SpeechSeparation 自然語言處理:建置提升服務型機器人對自然語言的語義理解API服務容器。 https://www.twman.org/AI/NLP 機器閱讀理解:透過翻譯SQuAD 1.0和2.0以及新增DRCD等數據集,重新優化原始bert模型,並且開發自有數據標註工具,用來解決服務型機器人需要關鍵字及正規表示式問題,建置API服務容器提升推論速度與準確度;將結果EM提升為 0.828,F1提升為0.899。 https://www.twman.org/AI/NLP/MRC 文本糾錯:基於ConvSeq2Seq及bert,並以pkuseg取代jieba,整合NER,優化模型與數據集,建置提升API推論容器速度與識別效果(EM: 0.7624,F1: 0.948)。 https://www.twman.org/AI/NLP/Correction 命名實體識別:整合拼音及分類機制,並採用ChineseAnnotator重新標註服務型機器人需求之商場等相關數據集,建置容器提升API推論容器速度與準確度(F1: 0.84)。 https://www.twman.org/AI/NLP/NER 文本相似度:基於TextCNN優化模型與數據集,建置容器提升API推論容器速度與語音服務問答準確度。 https://www.twman.org/AI/NLP/Similarity 文本分類:基於bert取代騰訊詞向量,優化模型與數據集及提升商場品牌識別分類準確度。 https://www.twman.org/AI/NLP/Classification #Security #軟體工程系統開發 #系統架構分析規劃 #軟體整合測試 #問題追蹤處理(Bug tracking) #自動化系統設計整合
Logo of the organization.

Senior Security Engineer

Jul 2014 - Dec 2015
1 yr 6 mos
Taipei City, Taiwan
Android malicious analysis and Evidence: A Hybrid Malware Probing System for Android Applications (APKProbe), which Combines both semantic-based static analysis to overcome packers and physical cluster machine-based dynamic analysis to bypass anti-sandboxing techniques. Custom Training, Architect Solution, and Cyber Security Research Android安全架構技術開發、惡意程式分析及偵測、研究。 資訊安全產品教育訓練、客戶端維護暨方案規劃。 資安設備監控,事件分析、事件處理及數位鑑識。 APKProbe:Android Apps混合惡意程式探測系統,結合基於語義的靜態分析來克服混淆編譯和基於實體機器的動態分析來規避反虛擬機技術。 #Android #規劃與管理防火牆 #軟體程式設計 #網路系統配置 #安裝與維護網路安全系統 #資訊設備環境設定
Logo of the organization.

Senior Security Engineer

Jan 2014 - Jul 2014
7 mos
Taipei City, Taiwan
Developed the toolkit for Digital Forensics cluster Services "Acer Cyber Evidence". Custom Training, Product Maintenance, and Cyber Security Research. 網路威脅與數位鑑識技術開發、惡意程式分析、研究。 資訊安全產品教育訓練、客戶端維護暨方案規劃。 資安設備監控,事件分析、事件處理及數位鑑識。 Acer Cyber Evidence:與Arcsight整合的數位鑑識工具 #規劃與管理防火牆 #網路安全架構分析與設計 #系統架構規劃與維護 #網路規劃管理 #系統整合分析 #系統架構規劃
Logo of the organization.

Assistant Researcher

Nov 2008 - Sep 2011
2 yrs 11 mos
Tainan City, Taiwan
Integrated with Diskless Remote Boot in Linux (DRBL) to develop the open-source toolkit for malware analysis "TWMAN". Custom Training, and Cyber Security Research. TWMAN (抬丸郎):基於WINDOWS的開源自動化惡意程式行為分析。 惡意程式分析技術開發與南部學術網路維運管理。 教育訓練、惡意程式分析、研究。 #規劃與管理防火牆 #網路規劃管理 #網路安全架構分析與設計 #系統架構規劃與維護 #伺服器網站管理維護 #網路系統配置

Education

Logo of the organization.
Doctor of Philosophy (PhD)
資訊工程學系
2010 - 2019
Description
基於深度學習的網路威脅異常分析 (Deep learning based anomaly analysis in cyber threats) Supervisor: Dr. Hung-Yu Kao;Intelligent Knowledge Management Laboratory (IKMLab) National Cheng Kung University, Computer Science and Information Engineering