Portfolio

Work list

By YoungJoong Kim 14 March 2020
Work list

Skills

  1. Languages
    : Python
    : C++ [git+revsic/cpp-obfuscator, git+utilForever/RosettaStone]

  2. ML Framework
    : Tensorflow [git+revsic/tf-glow-tts, git+revsic/tf-diffwave]
    : PyTorch [git+revsic/torch-nansypp, git+revsic/torch-flow-models]
    : Jax/Flax [git+revsic/jax-variational-diffwave]

  3. Windows Internal [git+revsic/cpp-veh-dbi]

  4. Fuzzing [git+revsic/agent-fuzz, git+theori-io/aixcc-afc-archive]

Opensource Contributions

  • sgl-project/sglang [GIT, PR#411], 2024.05.
    Cohere Command-R chat template supports.

  • linfeng93/BiTA [GIT, PR#4], 2024.02.
    Hard-coded path removal.

  • SqueezeBits/QUICK [GIT, PR#3], 2024.02.
    Exclude router projection layers from QUICK quantization.

  • microsoft/TransformerCompression [GIT, ISSUE#81], 2024.01.
    Mixtral 8x7B SliceGPT post-train pruning supports.

  • casper-hansen/AutoAWQ [GIT, PR#251], 2023.12.
    Mixtral 8x7B Activation-aware Quantization supports.

Projects - Fuzzing

  1. BranchFlipper: Agentic Fuzz Blocker Resolution [GIT, whitepaper], 2025.
    : Unlocking Fuzz Blockers with Coverage-Grounded LLMs, part of DARPA AIxCC (Team Theori)

  2. AgentFuzz: Agentic Fuzz Harness Generation [GIT, blog], 2024.
    : LLM Agent-based fuzz-driver generation, inspired by PromptFuzz[arXiv:2312.17677]

Projects - Machine Learning

  1. AlphaZero Connect6 [GIT], 2018.
    : AlphaZero training framework for game Connect6 written in Rust with C++, Python interface.

  2. Behavior based Malware Detection Using Branch Data [GIT], 2017.
    : Classify malware from benign software using branch data via LSTM based on Tensorflow

Projects - Windows Internal

  1. cpp-veh-dbi [GIT], 2019.
    : C++ implementation of vectored exception handler based simple dynamic binary instrumentation tools.

  2. Branch Tracer [GIT], 2019.
    : C++ implementation of dll-based windows debugger for tracking branching instruction via vectored exception handler.

  3. Code-Injector [GIT], 2018.
    : C++ implementation of several code injection techniques like dll injection, queue user apc.

  4. AntiDebugging [GIT], 2017.
    : C++ implementation for defending windows debugger from attaching the target process.

Projects

  1. cpp-concurrency [GIT], 2019.
    : C++ implementation of golang-style concurrency supports, thread pool, channel, wait-group

  2. cpp-obfuscator [GIT], 2019.
    : C++ implementation of compile time string and routine obfuscator.

  3. RosettaStone [GIT], 2018.
    : C++ implementation of game ‘Hearthstone’ as training environment and A.I. for future work.

  4. PacketInjector [GIT], 2016.
    : C++ implementation of simple packet detector and injector.

  5. ELF Code Virtualization, 2015.
    : ELF (Executable Linkable Format) Virtualized Code Protection

Paper implementations

  • torch-flow-models [GIT], 2025.02.
    : PyTorch implementations of various generative models, +17

  • torch-nansy++ [GIT], 2022.12.
    : NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis, openreview, 2022.

  • torch-whisper-guided-vc [GIT], 2022.12.
    : Torch implementation of Whisper-guided DDPM based Voice Conversion

  • torch-nansy [GIT], 2022.09.
    : Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations, Choi et al., 2021.

  • torch-retriever-vc [GIT], 2022.04.
    : Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph, Yin et al., 2022.

  • torch-diffusion-wavegan [GIT], 2022.03.
    : Parallel waveform generation with DiffusionGAN, Xiao et al., 2021.

  • torch-tacotron [GIT], 2022.02.
    : PyTorch implementation of Tacotron, Wang et al., 2017.

  • tf-mlptts [GIT], 2021.09.
    : Tensorflow implementation of MLP-Mixer based TTS.

  • jax-variational-diffwave [GIT], [arXiv:2107.00630], 2021.09.
    : Variational Diffusion Models

  • tf-glow-tts [GIT] [arXiv:2005.11129], 2021.07.
    : Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search

  • tf-survae-flows [GIT], [arXiv:2007.023731], 2021.05.
    : SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows

  • tf-diffwave [GIT] [arXiv:2009.09761], 2020.10.
    : DiffWave: A Versatile Diffusion Model for Audio Synthesis, Zhifeng Kong et al., 2020.

  • Rewriting-A-Deep-Generative-Models [GIT] [arXiv:2007.15646], 2020.09.
    : Rewriting a Deep Generative Model, David Bau et al., 2020.

  • tf-alae [GIT] [arXiv:2004.04467], 2020.09.
    : Adversarial Latent Autoencoders, Stanislav Pidhorskyi et al., 2020.

  • tf-neural-process [GIT] [arxiv: NP, CNP, ANP], 2019.05
    : Neural process, Conditional Neural Process, Attentive Neural Process

  • tf-vanilla-gan [GIT] [arXiv:1406.2661], 2018.01.
    : Generative Adversarial Nets, Ian J. Goodfellow et al., 2014.

School Works

  1. PA-2025-1H [GIT]
    : Lab notes on “Programming Analysis” in Seoul National University

  2. HYU-ITE2038 [GIT]
    : Lab notes on “Database Systems and Applications” in Hanyang University

  3. HYU-CSE4007 [GIT]
    : Lab notes on “Artificial Intelligence” in Hanyang University

  4. HYU-ELE3021 [GIT]
    : Lab notes on “Operating System” in Hanyang University

Papers

  1. Behavior Based Malware Detection Using Branch Data
    : 2017 KIISE Korea Computer Science Conference, 2017.

Presentations

  1. Prompt Engineering Trends
    : Theori, OpenTRS, 2025.01.16., 2025.02.18.

  2. Math for A.I., Generative Models
    : Mapo High School, 2023.11.28.

  3. The 2nd AI & Dining. Virtual Human and Generative Models
    : Sangmyung University, 2022.09.22.

  4. Deep learning and A.I.
    : Danggok High School, 2022.08.30.

  5. 2022 A.I.U. Research generative models in Startup [Google Drive]
    : A.I.U. 2022 AI Confrerence, 2022.05.

  6. Developing Environment for RL
    : Nexon Developers Conference 2019 as team RosettaStone, 2019.

  7. GP to NP: Gaussian process and Neural Process
    : A.I.U 1st Open AI Conference, 2018.

  8. Hearthstone++: Hearthstone simulator with reinforcement learning
    Deep Learning Camp Jeju, 2018.

  9. Behavior based Malware Detection Using Branch Data
    : CodeGate 2017 Junior, 2017.

Awards

  1. DARPA, AIxCC, 3rd Place; Team Theori
    Defense Advanced Research Projects Agency, AI Cyber Challenge, 3rd Place($1.5M), 2025.08

  2. KISA, 2016 Software Contest,
    Application Security Section 2nd Prize (Minister of Interior Award) 2016.09

Educations

  1. M.S. Department of Computer Science and Engineering
    Seoul National University, Visual & Geometric Intelligence Lab (2025.03. ~ )

  2. B.S. Major, Department of Computer Science and Engineering
    Hanyang University (2018.03. ~ 2025.02.)

  3. Minor, Department of Mathematics
    Hanyang University (2019.03. ~ 2025.02.)

  4. Vulnerability Analysis Track
    : 5th KITRI BoB (2016.05. ~ 2017.03.)

  5. Department of Information and Communication Technology
    : Sunrin Internet High School (2015.03. ~ 2017.02.)

Works

  1. AI for Offensive Security, Freelance Researcher
    Theori (2025.02. ~ 2025.08.)

  2. AI for Offensive Security, Senior Researcher
    Theori (2024.10. ~ 2025.02.)

  3. Research Team Lead
    Theori (2023.08. ~ 2024.10.)

  4. Video Synthesis, AI Researcher
    LionRocket (2021.10. ~ 2022.10., 2023.03. ~ 2023.08.)

  5. Research Team Lead
    LionRocket (2021.04. ~ 2023.08.)

  6. Speech Synthesis, AI Researcher
    LionRocket (2019.09. ~ 2021.10., 2022.10. ~ 2023.02.)