Profile
Alternative Military Service Status : on duty (2020/11/27 ~ 2023/09/26
)
Links
kozistr@gmail.com | |
Github | https://github.com/kozistr |
Kaggle | https://www.kaggle.com/kozistr |
https://www.linkedin.com/in/kozistr |
Interests
- Lots of real-world challenges like Kaggle
- Audio/Speech Domains
- End to End Speaker Diarization
- Speaker Verifications
- Computer Vision Domains
- especially the medical domain
Previously, I was also interested in offensive security, kind of Reverse Engineering, Linux Kernel Exploitation.
Challenges & Awards
Machine Learning
-
Kaggle Challenges :: Kaggle Challenges :: Competition Expert
- Google Brain - Ventilator Pressure Prediction - team, top 1% (20 / 2605), Private 0.1171 - solution (2021.)
- SIIM-FISABIO-RSNA COVID-19 Detection - solo, top 4% (47 / 1305), Private 0.612 - solution (2021.)
- Shopee - Price Match Guarantee - solo, top 7% (166 / 2426), Private 0.725 (2021.)
- Cornell Birdcall Identification - team, top 2% (24 / 1395), Private 0.631 - towarddatascience (2020.)
- ALASKA2 Image Steganalysis - solo, top 9% (93 / 1095), Private 0.917 (2020.)
- Tweet Sentiment Extraction - solo, top 4% (84 / 2227), Private 0.71796 (2020.)
- Flower Classification with TPUs - solo, top 4% (27 / 848), Private 0.98734 (2020.)
- Kaggle Bengali.AI Handwritten Grapheme Classification - solo, top 4% (67 / 2059), Private 0.9372 (2020.)
- Kaggle Kannada MNIST Challenge - solo, top 3% (28 / 1214), Private 0.99100 (2019.)
-
NAVER NLP Challenge :: NAVER NLP Challenge 2018
- Final - Semantic Role Labeling (SRL) 6th place - oral presentation
-
A.I R&D Challenge :: A.I R&D Challenge 2018
- Final - Fake or Real Detection - as Digital Forensic Team
-
NAVER A.I Hackathon :: NAVER A.I Hackathon 2018
-
TF-KR Challenge :: Facebook TF-KR MNIST Challenge
- TF-KR MNIST Challenge - Top 9, 3rd price, ACC 0.9964
Hacking
-
Boot2Root CTF 2018 :: 2nd place (Demon + alpha)
-
Harekaze CTF 2017 :: 3rd place (SeoulWesterns)
-
WhiteHat League 1 (2017) :: 2nd place (Demon)
- Awarded by 한국정보기술연구원 Received an award of $3,000
Work Experience
Company
Data Scientist, Toss core, (2021.12.06 ~ present)
- Working as full-time.
- Developed the text classification model to categorize users' reviews.
- Visualize the summarized trend of the keywords, which show the point of the opinion.
- Boost to analyze the users who give feedback with rich information. (may help to boost
NPS score
)
- Developed the robust captcha model to predict numeric captchas.
- light-weighted CNN model for real-time inference (about
~ 1000 TPS
for batch transaction,~ 50 TPS
for a sample on CPU) - Build augmentations which fit in the domain to build a robust model.
- Save $10,000 ~ 30,000 / year
- In A/B (online) test,
google vision OCR
vsNew Captcha Model
- Accuracy : improved 50%p (
49%
to95%
) - latency (p95) : reduced by x80 (about
1000ms
to12ms
)
- Accuracy : improved 50%p (
- light-weighted CNN model for real-time inference (about
- Developed the model to forecast the transactions' category to purchase next month & few weeks.
- Transformer-based architecture (customed with newly proposed methods).
- Calibration-aware training.
- In A/B (online) test,
previous ML model
vsAdsClassifier
(statistically significantp-value < 0.05
)- Conversion : soon!
- CTR : soon!
- Developed the loan overdue prediction model for BNPL (CSS model)
- EDA to find the useful features correlated with the overdue user.
- Build the robustness CV & ensemble strategy in an aspect of the on/offline performance.
- Developed the card category classification model.
- Transformer-based architecture, about
900 TPS
on a single GPU. - Handle noisy-text (transaction) & label, class-imbalanced problem.
- Transformer-based architecture, about
- Contributed to the team culture (e.g. collaboration tools, style-guides, etc).
Machine Learning Researcher, Watcha, (2020.06.22 ~ 2021.12.03)
- Worked as full-time.
- Developed a new sequential recommendation architecture. (named
Trans4Rec
)- Newly proposed transformer architecture to improve the performance in a genernal manner.
- Apply proper post-processing logic into the model.
- In A/B (online) test,
FutureFLAT
vsTrans4Rec
(statistically significantp-value < 0.01
)- Click Ratio : improved 1.01%
- Developed a music recommendation system (prototype)
- Developed a training recipe to train sequential recommendation architecture. (named
FutureFLAT
)- Build Future module to understand better at the time of inference.
- Apply augmentations to the various features, leads to performance gain & robustness.
- In A/B (online) test,
FLAT
vsFutureFLAT
(statistically significantp-value < 0.05
)- Compared to the previous model (
FLAT
), there’s no (statistically significant) improvments. - However, it still seems to be better on
the offline metrics
&training stability
. So, we chose to use it.
- Compared to the previous model (
- In A/B (online) test,
Div2Vec
vsFutureFLAT
(statistically significantp-value < 0.05
)- *Viewing Days (mean) : improved 1.012%
- *Viewing Minutes (median) : improved 1.015%
- Developed a model to predict expected users' view-time of the contents.
- Predict how many and how much time people are going to watch the content before the content supplied.
- Find out which features impact users' watches.
- Developed a pipeline to recognize main actors from the poster and still-cut images.
- Utilize SOTA face detector & recognizer.
- Optimize pre/post processing routines for low
latency
.
- Developed a novel sequential recommendation architecture to recommend what content to watch next. (named
FLAT
)- In A/B (online) test,
previous algorithms
vsFLAT
(statistically significantp-value < 0.05
)- Paid Conversion : improved 1.39%p+
- *Viewing Days (mean) : improved 0.25%p+
- *Viewing Minutes (median) : improved 4.10%p+
- Click Ratio : improved 4.30%p+
- Play Ratio : improved 2.32%p+
- In A/B (online) test,
- Developed Image Super-Resolution model to upscale movie & tv poster, still-cut images.
- Optimize the codes for
low latency
&memory-efficiency
on CPU. - An internal evaluation (qualitative evaluation by the designers), catches details better & handles higher resolution & takes a little time.
- Optimize the codes for
% *Viewing Days
: how many days are users active on an app each month.
% *Viewing Minutes
: how many minutes the user watched the contents.
Machine Learning Engineer, Rainist, (2019.11.11 ~ 2020.06.19)
- Worked as full-time.
- Developed the card & bank account transaction category classification models, designed light-weight purpose for the low latency. (now on service)
- In A/B (online) test (statistically significant
p-value < 0.05
)- *Accuracy : improved about 25 ~ 30%p
- In A/B (online) test (statistically significant
- Developed the RESTful API server to serve (general purpose) machine learning models.
- about 1M MAU service, 500K ~ 1M transactions / day (1 transaction = (median) about 100 samples).
- Utilized
inference-aware framework
(onnx) to reduce the latency.- median 100 ~ 200ms / transaction.
- zero failure rate (0 40x, 50x errors)
- Deployed & managed with Kubernetes, utilized open source project.
- Developed the classification model for forecasting the possibility of loan overdue.
% *Accuracy
: how many people don't update/change their transactions' category.
Machine Learning Engineer, VoyagerX, (2019.01.07 ~ 2019.10.04)
- Worked as an intern.
- Developed speaker verification, diarization models & logic for recognizing the arbitrary speakers recorded from the noisy (real-world) environment.
- Developed a hair image semantic segmentation / image in-paint / i2i domain transfer model for swapping hair domains naturally.
Penetration Tester, ELCID, (2016.07 ~ 2016.08)
- Worked as a part-time job.
- Penetrated some products related to network firewall and anti-virus products.
Out Sourcing
- Developed Korean University Course Information Web Parser (About 40 Universities). 2 times, (2017.7 ~ 2018.3)
- Developed AWS CloudTrail logger analyzer / formatter. (2019.09 ~ 2019.10)
Lab
HPC Lab, KoreaTech, Undergraduate Researcher, (2018.09 ~ 2018.12)
- Wrote a paper about an improved TextCNN model to predict a movie rate.
Publications
Paper
[1] Kim et al, CNN Architecture Predicting Movie Rating, 2020. 01.
- Wrote about the CNN Architecture, which utilizes a channel-attention method (SE Module) to TextCNN model, brings performance gain over the task while keeping its latency, generally.
- Handling un-normalized text with various convolution kernel sizes and spatial dropout
- Selected as one of the
highlight papers
for the first half of 2020
Conferences/Workshops
[1] kozistr_team
, presentation NAVER NLP Challenge 2018 SRL Task
- SRL Task, challenging w/o any domain knowledge. Presented about trials & errors during the competition
Journals
[1] zer0day, Windows Anti-Debugging Techniques (CodeEngn 2016) Sep. 2016. PDF
- Wrote about lots of anti-reversing / debugging (A to Z) techniques avail on window executable binary
Posts
[1] kozistr (as a part of team, Dragonsong
) towarddatascience
- Wrote about audio classifier with deep learning based on the Kaggle challenge where we participated
Personal Projects
Machine/Deep Learning
Generative Models
-
GANs-tensorflow :: Lots of GAN codes :) :: Generative Adversary Networks
- ACGAN-tensorflow :: Auxiliary Classifier GAN in tensorflow :: code
- StarGAN-tensorflow :: Unified GAN for multi-domain :: code
- LAPGAN-tensorflow :: Laplacian Pyramid GAN in tensorflow :: code
- BEGAN-tensorflow :: Boundary Equilibrium in tensorflow :: code
- DCGAN-tensorflow :: Deep Convolutional GAN in tensorflow :: code
- SRGAN-tensorflow :: Super-Resolution GAN in tensorflow :: code
- WGAN-GP-tensorflow :: Wasserstein GAN w/ gradient penalty in tensorflow :: code
- ... lots of GANs (over 20) :)
Super Resolution
-
Single Image Super Resolution :: Single Image Super-Resolution (SISR)
I2I Translation
- Improved Content Disentanglement :: tuned version of 'Content Disentanglement' in pytorch :: code
Style Transfer
-
Image-Style-Transfer :: Image Neural Style Transfer
- style-transfer-tensorflow :: Image Style-Transfer in tensorflow :: code
Text Classification/Generation
Speech Synthesis
-
Tacotron-tensorflow :: Text To Sound (TTS)
- tacotron-tensorflow :: lots of TTS models in tensorflow ::
code
- tacotron-tensorflow :: lots of TTS models in tensorflow ::
Optimizer
-
pytorch-optimizer :: Bunch of optimizer implementations in PyTorch
- pytorch_optimizer :: Bunch of optimizer implementations in PyTorch with clean-code, strict types. Also, including useful optimization ideas. Most of the implementations are based on the original paper, but I added some tweaks. :: code
-
AdaBound :: Optimizer that trains as fast as Adam and as good as SGD
- AdaBound-tensorflow :: AdaBound Optimizer implementation in tensorflow :: code
-
RAdam :: On The Variance Of The Adaptive Learning Rate And Beyond in tensorflow
- RAdam-tensorflow :: RAdam Optimizer implementation in tensorflow :: code
R.L
- Rosseta Stone :: Hearthstone simulator using C++ with some reinforcement learning :: code
Open Source Contributions
- syzkaller :: New Generation of Linux Kernel Fuzzer :: #575
- simpletransformers :: Transformers made simple w/ training, evaluating, and prediction possible w/ one line each. :: #290
- pytorch-image-models :: PyTorch image models, scripts, pretrained weights :: #1058, #1069
- deit :: DeiT: Data-efficient Image Transformers :: #140, #147, #148
- MADGRAD :: MADGRAD Optimization Method :: #11
- tensorflow-image-models :: TensorFlow Image Models (tfimm) is a collection of image models with pretrained weights, obtained by porting architectures from timm to TensorFlow :: #61
Plug-Ins
IDA-pro plug-in - Golang ELF binary (x86, x86-64), RTTI parser
- Recover stripped symbols & information and patch byte-codes for being able to hex-ray
Security, Hacking
CTFs, Conferences
- POC 2016 Conference Staff
- HackingCamp 15 CTF Staff, Challenge Maker
- CodeGate 2017 OpenCTF Staff, Challenge Maker
- HackingCamp 16 CTF Staff, Challenge Maker
- POX 2017 CTF Staff, Challenge Maker
- KID 2017 CTF Staff, Challenge Maker
- Belluminar 2017 CTF Staff
- HackingCamp 17 CTF Staff, Challenge Maker
- HackingCamp 18 CTF Staff, Challenge Maker
Teams
Hacking Team, Fl4y. Since 2017.07 ~
Hacking Team, Demon by POC. Since 2014.02 ~ 2018.08
Educations
Senior in Computer Engineering from KUT
Presentations
2018
[2] Artificial Intelligence ZeroToAll, Apr 2018.
[1] Machine Learning ZeroToAll, Mar 2018.
2015
[1] Polymorphic Virus VS AV Detection, Oct 2015.
2014
[1] Network Sniffing & Detection, Oct, 2014.