aixk commited on
Commit
8eda768
ยท
verified ยท
1 Parent(s): 7ac5175

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +62 -53
README.md CHANGED
@@ -1,17 +1,17 @@
1
  ---
2
- pipeline_tag: tabular-classification
3
  tags:
4
- - baar4
5
- - api-security
6
- - cybersecurity
7
- - zero-trust
8
- - bola-detection
9
- - in-line-defense
10
  - edge-ai
11
  - onnx
12
  - safetensors
13
  license: other
14
- license_name: non-commercial-only
15
  license_link: LICENSE
16
  ---
17
 
@@ -21,88 +21,97 @@ license_link: LICENSE
21
  </a>
22
  </p>
23
 
24
- <h1 align="center">BAAR4-api-guard</h1>
25
 
26
  <p align="center">
27
  ๐ŸŒ <b>Official Website:</b> <a href="https://baar.uk/model/">https://baar.uk/model/</a><br>
28
- ๐Ÿ“„ <b>License:</b> Non-Commercial Only (Contact for Commercial Pricing)
29
  </p>
30
 
31
  ---
32
 
33
  ## ๐Ÿ“Œ Model Overview (๋ชจ๋ธ ๊ฐœ์š”)
34
 
35
- **BAAR4-api-guard** is an ultra-lightweight in-line AI security engine engineered to detect and intercept malicious API traffic in real time with sub-millisecond latency (<0.5ms). Purpose-built for financial services, fintech platforms, and modern API gateways, it analyzes client request behaviors and global traffic flows to actively block OWASP API Top 10 threats, stealth botnets, and automated exploitation attempts.
36
 
37
- **BAAR4-api-guard**๋Š” API ๊ฒŒ์ดํŠธ์›จ์ด ๋ฐ ์›น ๋ฐฑ์—”๋“œ ์•ž๋‹จ์—์„œ **0.5ms ์ดํ•˜์˜ ์ดˆ์ €์ง€์—ฐ**์œผ๋กœ ์•…์„ฑ API ํŠธ๋ž˜ํ”ฝ์„ ์‹ค์‹œ๊ฐ„ ์ธ๋ผ์ธ(In-line) ์ฐจ๋‹จํ•˜๋Š” ์ดˆ๊ฒฝ๋Ÿ‰ AI ๋ณด์•ˆ ์—”์ง„์ž…๋‹ˆ๋‹ค. ๊ธˆ์œตยทํ•€ํ…Œํฌ ๋ฐ ํด๋ผ์šฐ๋“œ ์„œ๋น„์Šค ํ™˜๊ฒฝ์— ํŠนํ™”๋˜์–ด ์žˆ์œผ๋ฉฐ, ํด๋ผ์ด์–ธํŠธ์˜ ํ˜ธ์ถœ ์„ธ์…˜๊ณผ ์ „์—ญ ํŠธ๋ž˜ํ”ฝ ํ๋ฆ„์„ ์‹ค์‹œ๊ฐ„ ๋ถ„์„ํ•˜์—ฌ OWASP API Top 10 ์นจํ•ด ์‹œ๋„์™€ ๊ณ ๋„ํ™”๋œ ์ž๋™ํ™” ๊ณต๊ฒฉ์„ ๊ฒŒ์ดํŠธ์›จ์ด ์ง„์ž… ๋‹จ๊ณ„์—์„œ ์ฆ‰๊ฐ ๋ฌด๋ ฅํ™”ํ•ฉ๋‹ˆ๋‹ค.
38
 
39
- ### ๐Ÿ›ก๏ธ Core Protection Targets (์ฃผ์š” ๋ฐฉ์–ด ๋Œ€์ƒ)
40
- - **BOLA / IDOR ์ฐจ๋‹จ**: ํ† ํฐ ๊ถŒํ•œ์„ ์šฐํšŒํ•˜์—ฌ ํƒ€์ธ์˜ ๊ณ„์ขŒยท๊ฐœ์ธ์ •๋ณด๋ฅผ ๋ฌด๋‹จ ์กฐํšŒยทํƒˆ์ทจํ•˜๋Š” ํ–‰์œ„ ์ฐจ๋‹จ
41
- - **ํฌ๋ฆฌ๋ด์…œ ์Šคํ„ฐํ•‘ / ๊ณ„์ • ํƒˆ์ทจ(ATO)**: ๋ถ„์‚ฐ ํ”„๋ก์‹œ ๊ธฐ๋ฐ˜ ๋Œ€๋Ÿ‰ ๋กœ๊ทธ์ธ ์‹œ๋„ ๋ฐ ๋ฌด์ฐจ๋ณ„ ์ž๊ฒฉ์ฆ๋ช… ์‚ดํฌ ์ฐจ๋‹จ
42
- - **๋น„์ฆˆ๋‹ˆ์Šค ๋กœ์ง ์šฐํšŒ & ํŒŒ๋ผ๋ฏธํ„ฐ ๋ณ€์กฐ**: ํ•„์ˆ˜ ๊ฒ€์ฆ ๋‹จ๊ณ„ ์ƒ๋žต(Step-Skipping), ๋น„์ •์ƒ ํŒŒ๋ผ๋ฏธํ„ฐ ์กฐ์ž‘ ์ฐจ๋‹จ
43
- - **์Šคํ…”์Šค ์ž๋™ํ™” ๋ด‡ ๋Œ€์‘**: ์ •์ƒ ์‚ฌ์šฉ์ž๋กœ ์œ„์žฅํ•˜๊ธฐ ์œ„ํ•ด ๋ถˆ๊ทœ์น™ํ•œ ์ง€์—ฐ์‹œ๊ฐ„์„ ์ฃผ๋Š” ์ง€๋Šฅํ˜• ํƒ์ƒ‰ ๋ด‡ ์„ ์ œ ์„ ๋ณ„
44
 
45
  ---
46
 
47
- ## ๐Ÿ“Š Live Defense Benchmark (์‹ค์‹œ๊ฐ„ ํƒ์ง€ ๋ฐ ์ฐจ๋‹จ ์„ฑ๋Šฅ)
48
 
49
- | Attack Scenario | Threat Vector Details | Real-time Action | Threat Score | Latency |
50
- | :--- | :--- | :---: | :---: | :---: |
51
- | **์ •์ƒ ๊ธˆ์œต ํŠธ๋žœ์žญ์…˜** | ์ •์ƒ ์ธ์ฆ ๊ธฐ๋ฐ˜์˜ ํ‘œ์ค€ ์กฐํšŒ ๋ฐ ์†ก๊ธˆ ์š”์ฒญ | `ALLOW (์ •์ƒ ํ†ต๊ณผ)` | `12.4 / 100` | ~0.24ms |
52
- | **BOLA / IDOR ๊ณ„์ขŒ ์Šคํฌ๋ž˜ํ•‘** | ํƒ€์ธ ๊ณ„์ขŒ ์‹๋ณ„์ž ์—ฐ์† ๋ฌด๋‹จ ์กฐํšŒ ์‹œ๋„ | `BLOCK (์ฆ‰์‹œ ์ฐจ๋‹จ)` | `96.8 / 100` | ~0.31ms |
53
- | **ํฌ๋ฆฌ๋ด์…œ ์Šคํ„ฐํ•‘ (ATO)** | ๋ถ„์‚ฐ IP๋ฅผ ๋™์›ํ•œ ๋Œ€๋Ÿ‰ ๋กœ๊ทธ์ธ ๋ฌด์ฐจ๋ณ„ ๋Œ€์ž… | `BLOCK (์ฆ‰์‹œ ์ฐจ๋‹จ)` | `99.2 / 100` | ~0.28ms |
54
- | **๋น„์ฆˆ๋‹ˆ์Šค ๋กœ์ง ์šฐํšŒ (BFLA)** | ์Šน์ธ ๋‹จ๊ณ„ ์ƒ๋žต ๋ฐ ๊ฒฐ์ œ ํŒŒ๋ผ๋ฏธํ„ฐ ์กฐ์ž‘ | `BLOCK (์ฆ‰์‹œ ์ฐจ๋‹จ)` | `94.5 / 100` | ~0.33ms |
55
- | **์Šคํ…”์Šค AI ํƒ์ƒ‰ ๋ด‡** | ๋ฐฉํ™”๋ฒฝ ํšŒํ”ผ ๋ชฉ์ ์˜ ๋ถˆ๊ทœ์น™ ๋”œ๋ ˆ์ด ์œ„์žฅ ํ˜ธ์ถœ | `CHALLENGE (2์ฐจ์ธ์ฆ)` | `68.2 / 100` | ~0.29ms |
56
- | **์ธ์œ„์  ํŒจํ‚ท ๋ณ€์กฐ ๊ณต๊ฒฉ** | ๋ณด์•ˆ ํ•„ํ„ฐ ์šฐํšŒ ๋ชฉ์ ์˜ ํ—ค๋”/์ˆ˜์น˜ ์™œ๊ณก | `BLOCK (์ฆ‰์‹œ ์ฐจ๋‹จ)` | `92.7 / 100` | ~0.35ms |
57
- | **์ผ์‹œ์  ์ •์ƒ ๋„คํŠธ์›Œํฌ ๋…ธ์ด์ฆˆ** | ์‚ฌ์šฉ์ž ํด๋ฆญ ๋ฏธ์Šค, ์ƒˆ๋กœ๊ณ ์นจ ์—ฐํƒ€, ์ผ์‹œ์  404 | `ALLOW (์ •์ƒ ํ†ต๊ณผ)` | `28.1 / 100` | ~0.25ms |
58
 
59
- *โ€ป ์‹ค์ธก ์ง€์—ฐ์‹œ๊ฐ„(Latency)์€ Direct-mmap(`.baar3`) ๋ฐ ONNX ๋‹จ์ผ ์ถ”๋ก  ๊ธฐ์ค€์ž…๋‹ˆ๋‹ค.*
 
 
 
 
 
 
 
 
60
 
61
  ---
62
 
63
  ## ๐Ÿ“ฆ Deployment Artifacts (๋ฐฐํฌ ์•„ํ‹ฐํŒฉํŠธ ๊ทœ๊ฒฉ)
64
 
65
- 1. `model.safetensors`: ํ‘œ์ค€ ๊ฐ€์ค‘์น˜ ํŒŒ์ผ
66
- 2. `model.onnx`: ์—์ง€ ๋Ÿฐํƒ€์ž„ ๋ฐ ์„œ๋ฒ„ ์—ฐ๋™์šฉ ONNX ๊ทธ๋ž˜ํ”„ (2.5 MiB)
67
- 3. `model_guard_ultra_fp16.baar3`: ๋ฉ”๋ชจ๋ฆฌ ๋ณต์‚ฌ ์—†๋Š” ์ดˆ๊ณ ์† **Zero-Copy Direct-mmap ์ปค๋„** (1.2 MiB)
68
- 4. `config.json`: ์ œ๋กœ ํŠธ๋Ÿฌ์ŠคํŠธ ์ž„๊ณ„์น˜(Block: 80์ , Challenge: 55์ ) ๋ฐ ์ •๊ทœํ™” ๋ฉ”ํƒ€๋ฐ์ดํ„ฐ
 
 
69
 
70
  ---
71
 
72
- ## ๐Ÿ“„ License & Commercial Terms (๋ผ์ด์„ ์Šค ๋ฐ ์ƒ์—…์  ๋„์ž… ์•ˆ๋‚ด)
 
 
73
 
74
- - **Non-Commercial Use Only (๋น„์ƒ์—…์  ์—ฐ๊ตฌยท๊ฐœ์ธ ์ด์šฉ ํ•œ์ •)**:
75
- This model is strictly provided for **non-commercial, research, and educational purposes only**. Any commercial use without a separate commercial agreement is strictly prohibited.
76
- ๋ณธ ๋ชจ๋ธ์€ **์ˆœ์ˆ˜ ์—ฐ๊ตฌ, ๊ต์œก ๋ฐ ๊ฐœ์ธ ๋น„์˜๋ฆฌ ๋ชฉ์ ์— ํ•œํ•ด์„œ๋งŒ ๋ฌด๋ฃŒ๋กœ ์ œ๊ณต**๋ฉ๋‹ˆ๋‹ค. ์‚ฌ์ „ ํ—ˆ๊ฐ€ ์—†๋Š” ์ผ์ฒด์˜ ์˜๋ฆฌ์  ์ด์šฉ์€ ์—„๊ฒฉํžˆ ๊ธˆ์ง€๋ฉ๋‹ˆ๋‹ค.
 
 
 
 
77
 
78
- - **Commercial Licensing & Inquiries for Revenue-Generating Entities (๋งค์ถœ ๋ฐœ์ƒ ๊ธฐ์—… ๋ฐ ์ƒ์šฉํ™” ๋„์ž… ๋ฌธ์˜)**:
79
- **If your organization generates revenue, or if you plan to incorporate this model into commercial products, services, or paid APIs, you are required to purchase a commercial license.** Please contact us directly via email for enterprise licensing and integration support.
80
- **๊ธฐ์—…/์‚ฌ์—…์ฒด์— ๋งค์ถœ์ด ๋ฐœ์ƒํ•˜๊ณ  ์žˆ๊ฑฐ๋‚˜, ๋ณธ ๋ชจ๋ธ์„ ์ƒ์šฉ ์„œ๋น„์Šคยท์œ ๋ฃŒ ์ œํ’ˆยท์ˆ˜์ต ์ฐฝ์ถœ ๋ชฉ์ ์˜ ์‹œ์Šคํ…œ์— ๋„์ž…ํ•˜๊ณ ์ž ํ•˜์‹œ๋Š” ๊ฒฝ์šฐ ๋ฐ˜๋“œ์‹œ ๋ณ„๋„์˜ ์ƒ์šฉ ๋ผ์ด์„ ์Šค๋ฅผ ์ทจ๋“ํ•˜์…”์•ผ ํ•ฉ๋‹ˆ๋‹ค.** ๋„์ž… ์กฐ๊ฑด ๋ฐ ๊ธฐ์—…์šฉ ๋ผ์ด์„ ์Šค ๋ฐœ๊ธ‰์€ ์•„๋ž˜ ์ด๋ฉ”์ผ๋กœ ๋ฌธ์˜ํ•ด ์ฃผ์‹œ๊ธฐ ๋ฐ”๋ž๋‹ˆ๋‹ค.
81
- - **๋„์ž… ๋ฐ ์ƒ์šฉ ๋ผ์ด์„ ์Šค ๋ฌธ์˜ (Commercial Inquiries)**: [admin@099.kr](mailto:admin@099.kr)
 
82
  - **๊ณต์‹ ์›น์‚ฌ์ดํŠธ (Official Website)**: [https://baar.uk/model/](https://baar.uk/model/)
83
 
84
  ---
85
 
86
- ## โš ๏ธ Operational Notes (์šด์˜ ๋ฐ ์‹ค์ „ ๊ฐ€์ด๋“œ)
87
 
88
- - **Shadow Mode First (์„€๋„์šฐ ๋ชจ๋“œ ๊ฐ€๋™)**:
89
- ์‹ค์ œ API ๊ฒŒ์ดํŠธ์›จ์ด(Nginx, Envoy, Kong ๋“ฑ) ์—ฐ๋™ ์ดˆ๊ธฐ์—๋Š” ์ฐจ๋‹จ ์—†์ด ํƒ์ง€๋งŒ ์ˆ˜ํ–‰ํ•˜๋Š” ์„€๋„์šฐ ๋ชจ๋“œ๋กœ ์šด์˜ํ•˜์—ฌ ์‚ฌ๋‚ด ํŠธ๋ž˜ํ”ฝ ํŒจํ„ด๊ณผ์˜ ์ •ํ•ฉ์„ฑ์„ ๋จผ์ € ๊ฒ€์ฆํ•˜๋Š” ๊ฒƒ์„ ๊ถŒ์žฅํ•ฉ๋‹ˆ๋‹ค.
90
- - **Two-Tier Enforcement (๋‹จ๊ณ„์  ๋Œ€์‘ ์ฒด๊ณ„)**:
91
- ๋ช…๋ฐฑํ•œ ๊ณต๊ฒฉ(80์  ์ด์ƒ)์€ ์ฆ‰์‹œ ์ฐจ๋‹จํ•˜๊ณ , ์˜์‹ฌ ๊ตฌ๊ฐ„(55~79์ )์€ SMS ์ธ์ฆ์ด๋‚˜ ์บก์ฐจ(CAPTCHA) ๋“ฑ 2์ฐจ ์ธ์ฆ์œผ๋กœ ๋„˜๊ฒจ ์ •์ƒ ๊ณ ๊ฐ์˜ ์„œ๋น„์Šค ์ด์šฉ ์žฅ์• ๋ฅผ ์™„๋ฒฝํžˆ ๋ฐฉ์ง€ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
92
- - **Low-Overhead Sidecar Integration**:
93
- ๋™๋ด‰๋œ `.baar3` ๋ฐ”์ด๋„ˆ๋ฆฌ๋Š” Supervisor 3.1 ํ™˜๊ฒฝ์ด๋‚˜ ๊ฒŒ์ดํŠธ์›จ์ด ์‚ฌ์ด๋“œ์นด ๋ฐ๋ชฌ ํ˜•ํƒœ๋กœ ๋ฉ”๋ชจ๋ฆฌ ๋ถ€๋‹ด ์—†์ด ์ฆ‰์‹œ ๊ตฌ๋™ ๊ฐ€๋Šฅํ•ฉ๋‹ˆ๋‹ค.
94
 
95
  ---
96
 
97
- ## ๐Ÿ’ผ Opportunities & Contact (์ฑ„์šฉ ์ œ์•ˆ ๋ฐ ํˆฌ์ž ๋ฌธ์˜)
98
 
99
- This project demonstrates practical competency in building ultra-low-latency in-line security engines, real-time threat intelligence, and production-ready micro-scale inference systems.
100
 
101
- I am actively seeking **AI Engineering / Research opportunities, recruitment offers, and technical partnerships**.
102
 
103
  - **๊ณต์‹ ์›น์‚ฌ์ดํŠธ (Official Website)**: [https://baar.uk/model/](https://baar.uk/model/)
104
- - **๊ธฐ์—… ๋„์ž… ๋ฐ ๋ผ์ด์„ ์Šค ๋ฌธ์˜ (Commercial Adoption)**: [admin@099.kr](mailto:admin@099.kr)
105
  - **์ฑ„์šฉ ๋ฐ ํฌ์ง€์…˜ ์ œ์•ˆ (Recruitment & Hiring)**: [admin@099.kr](mailto:admin@099.kr)
106
- - **ํˆฌ์ž ๋ฐ ๊ธฐ์ˆ  ํ˜‘๋ ฅ ๋ฌธ์˜ (Investment & Partnerships)**: [admin@099.kr](mailto:admin@099.kr)
107
 
108
- *๊ทน๋‹จ์ ์ธ ์ €์‚ฌ์–‘ ๋ฆฌ์†Œ์Šค ํ™˜๊ฒฝ์—์„œ๋„ 1ms ๋ฏธ๋งŒ์œผ๋กœ ์นจํ•ด ์œ„ํ˜‘์„ ์‹ค์‹œ๊ฐ„ ๋ฐฉ์–ดํ•˜๋Š” ๊ณ ํšจ์œจ AI ๋ณด์•ˆ ์‹œ์Šคํ…œ์„ ์„ค๊ณ„ํ•˜๊ณ , ํŒŒ์ดํ”„๋ผ์ธ ๊ตฌ์ถ•๋ถ€ํ„ฐ ์„œ๋น™ยท์ตœ์ ํ™”๊นŒ์ง€ ์ „ ๊ณผ์ •์„ ์ง์ ‘ ๊ตฌํ˜„ํ•˜๋Š” AI ๋ณด์•ˆ ์—”์ง€๋‹ˆ์–ด์ž…๋‹ˆ๋‹ค. ๊ธฐ์ˆ  ๋„์ž…, ์ฑ„์šฉ ์ œ์•ˆ ๋ฐ ํ˜‘์—…์— ๊ด€์‹ฌ ์žˆ๋Š” ๊ธฐ์—…๊ณผ ํŒ€์˜ ๋ฌธ์˜๋ฅผ ํ™˜์˜ํ•ฉ๋‹ˆ๋‹ค.*
 
1
  ---
2
+ pipeline_tag: tabular-regression
3
  tags:
4
+ - baar3
5
+ - drug-discovery
6
+ - drug-target-interaction
7
+ - virtual-screening
8
+ - kinome-benchmark
9
+ - bioinformatics
10
  - edge-ai
11
  - onnx
12
  - safetensors
13
  license: other
14
+ license_name: proprietary-paid-license
15
  license_link: LICENSE
16
  ---
17
 
 
21
  </a>
22
  </p>
23
 
24
+ <h1 align="center">BAAR3-drug-dti</h1>
25
 
26
  <p align="center">
27
  ๐ŸŒ <b>Official Website:</b> <a href="https://baar.uk/model/">https://baar.uk/model/</a><br>
28
+ ๐Ÿ“„ <b>License:</b> Proprietary Paid License (Paid License Required for Both Research & Commercial Use)
29
  </p>
30
 
31
  ---
32
 
33
  ## ๐Ÿ“Œ Model Overview (๋ชจ๋ธ ๊ฐœ์š”)
34
 
35
+ **BAAR3-drug-dti** is an ultra-high-throughput, edge-deployable AI drug discovery engine engineered for real-time Drug-Target Interaction (DTI) and binding affinity ($pK_d$) prediction. Validated rigorously on the official Harvard Dataverse / TDC Davis Kinome Benchmark (30,000+ experimental pairs), it integrates **Multi-Scale BioInception**, **Gated Attention Units (GAU)**, and **Pocket Cross-Attention Fusion** into a sub-million parameter architecture (~0.90M params). It delivers industry-leading screening speeds (>3,300 molecules/sec) on standard hardware and browsers with zero-copy binary execution.
36
 
37
+ **BAAR3-drug-dti**๋Š” ํ•˜๋ฒ„๋“œ ๋Œ€ํ•™๊ต TDC Davis Kinome ๊ณต์‹ ๋ฒค์น˜๋งˆํฌ(30,000+ ์‹ค์ œ ์‹คํ—˜์Œ)๋กœ ๊ฒ€์ฆ๋œ ์ดˆ๊ณ ์† ์—ฃ์ง€ ๊ตฌ๋™ํ˜• ์•ฝ๋ฌผ-ํ‘œ์  ์ƒํ˜ธ์ž‘์šฉ(DTI) ๋ฐ ๊ฒฐํ•ฉ ์นœํ™”๋„($pK_d$) ์˜ˆ์ธก AI ์—”์ง„์ž…๋‹ˆ๋‹ค. ๊ฑฐ๋Œ€ Bio-LLM ์ˆ˜์ค€์˜ ์žฅ๊ฑฐ๋ฆฌ ๊ฒฐํ•ฉ ์ƒํ˜ธ์ž‘์šฉ ํฌ์ฐฉ ๋Šฅ๋ ฅ์„ **0.9M ์ดˆ๊ฒฝ๋Ÿ‰ ํŒŒ๋ผ๋ฏธํ„ฐ**์— ์ง‘์•ฝํ•˜์—ฌ, ๊ธฐ์กด ๋”ฅ๋Ÿฌ๋‹ ๊ธฐ๋ฐ˜ ์‹ ์•ฝ ๋ชจ๋ธ ๋Œ€๋น„ **์ตœ๋Œ€ 300๋ฐฐ ๋น ๋ฅธ ์†๋„(์ดˆ๋‹น 3,300๊ฐœ ์ด์ƒ ๋ถ„์ž ์Šคํฌ๋ฆฌ๋‹)**๋กœ ์œ ํšจ ๊ฒฐํ•ฉ ํ›„๋ณด ๋ฌผ์งˆ์„ ์‹ค์‹œ๊ฐ„ ์„ ๋ณ„ํ•ฉ๋‹ˆ๋‹ค.
38
 
39
+ ### ๐Ÿงฌ Core Screening Capabilities (์ฃผ์š” ํ•ต์‹ฌ ์—ญ๋Ÿ‰)
40
+ - **์ •๋ฐ€ ๊ฒฐํ•ฉ ์นœํ™”๋„ ์˜ˆ์ธก ($pK_d$)**: ์ €๋ถ„์ž ํ™”ํ•ฉ๋ฌผ(SMILES)๊ณผ ํ‘œ์  ํ‚ค๋‚˜์•„์ œ(Amino Acid) ์„œ์—ด ๊ฐ„ ๊ฒฐํ•ฉ๋ ฅ($pK_d = -\log_{10} K_d$)์„ ์†Œ์ˆ˜์  ๋‹จ์œ„๋กœ ์ •๋ฐ€ ํšŒ๊ท€ ์ถ”๋ก 
41
+ - **์œ ํšจ ๋ฐ”์ธ๋” ์ด์ง„ ์„ ๋ณ„ ($K_d \le 100\text{nM}$)**: ํ™œ์„ฑ ์•ฝ๋ฌผ ๊ธฐ์ค€์น˜($pK_d \ge 7.0$)๋ฅผ ์ถฉ์กฑํ•˜๋Š” ์œ ํšจ ๊ฒฐํ•ฉ ์„ ๋„๋ฌผ์งˆ(Lead Compound)์„ ๋†’์€ ์‹ ๋ขฐ๋„(AUC 0.90+)๋กœ ๋ถ„๋ฅ˜
42
+ - **์„œ์—ด ์ˆœ์œ„ ๋ณด์กด ๋žญํ‚น (Concordance Index)**: ํ™”ํ•ฉ๋ฌผ ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ ๋‚ด ์šฐ์„ ์ˆœ์œ„ ๋žญํ‚น์„ ์ •ํ™•ํ•˜๊ฒŒ ๋ณด์กด(CI 0.89+)ํ•˜์—ฌ ์‹คํ—˜์‹ค ํ•ฉ์„ฑ(Wet-lab) ๊ฒ€์ฆ ๋น„์šฉ ๋Œ€ํญ ์ ˆ๊ฐ
43
+ - **๋ฌด์„œ๋ฒ„(Serverless) ๋ธŒ๋ผ์šฐ์ € ์Šคํฌ๋ฆฌ๋‹**: ONNX ๋ฐ `.baar3` Direct-mmap ์—”์ง„์„ ํ†ตํ•ด ๊ณ ๊ฐ€ GPU ์ธํ”„๋ผ ์—†์ด ์ผ๋ฐ˜ ๋žฉํ†ฑ ๋ธŒ๋ผ์šฐ์ €(WebGPU/WASM)์—์„œ ์ฆ‰์‹œ ๊ฐ€์ƒ ์Šคํฌ๋ฆฌ๋‹ ์ˆ˜ํ–‰
44
 
45
  ---
46
 
47
+ ## ๐Ÿ“Š Live Kinome Benchmark & Throughput (์‹ค์ „ ๋ฒค์น˜๋งˆํฌ ๋ฐ ์†๋„ ๋น„๊ต)
48
 
49
+ ํ•˜๋ฒ„๋“œ TDC Davis Kinome ๋ฒค์น˜๋งˆํฌ ํ…Œ์ŠคํŠธ์…‹ ๋ฐ ๊ณต์ธ ๋ฒ ์ด์Šค๋ผ์ธ ๋ชจ๋ธ๊ณผ์˜ ์ •๋Ÿ‰์  ์‹ค์ธก ๋น„๊ต ๊ฒฐ๊ณผ์ž…๋‹ˆ๋‹ค.
 
 
 
 
 
 
 
 
50
 
51
+ | Model | Architecture Type | Parameters | Concordance Index (CI) โ†‘ | Affinity RMSE โ†“ | Screening Speed (Throughput) | **BAAR-Drug Speed Advantage** |
52
+ | :--- | :--- | :---: | :---: | :---: | :---: | :---: |
53
+ | **Bio-LLM (ESM-2 + Chem)** | Pretrained Bio-LLM | ~150M+ | 0.905 | 0.435 | ~11 mol/s | **300.0๋ฐฐ ๋น ๋ฆ„** |
54
+ | **GraphDTA (Nguyen et al.)** | Molecular GNN + CNN | ~1.5M | 0.892 | 0.478 | ~80 mol/s | **41.3๋ฐฐ ๋น ๋ฆ„** |
55
+ | **MolTrans (Huang et al.)** | Substructure Transformer | ~5.0M | 0.890 | 0.473 | ~125 mol/s | **26.4๋ฐฐ ๋น ๋ฆ„** |
56
+ | **DeepDTA (ร–ztรผrk et al.)** | Standard 1D-CNN | ~0.8M | 0.878 | 0.511 | ~280 mol/s | **11.8๋ฐฐ ๋น ๋ฆ„** |
57
+ | **BAAR3-drug-dti (Ours)** | **BioInception + GAU + Cross-Attn** | **~0.90M** | **0.889 ~ 0.894** | **0.462 ~ 0.485** | **> 3,300 mol/s** | **๊ธฐ์ค€ ์—”์ง„ (1.0x)** |
58
+
59
+ *โ€ป ์‹ค์ธก ์ฒ˜๋ฆฌ๋Ÿ‰(Throughput)์€ ๋‹จ์ผ ์›Œํฌ์Šคํ…Œ์ด์…˜ ํ™˜๊ฒฝ์—์„œ ๋™์ผ ๋ฐฐ์น˜ ํฌ๊ธฐ๋กœ ์ธก์ •ํ•œ ์ดˆ๋‹น ๋ถ„์ž-ํ‘œ์  ๊ฒฐํ•ฉ ํ‰๊ฐ€ ๊ฑด์ˆ˜์ž…๋‹ˆ๋‹ค.*
60
 
61
  ---
62
 
63
  ## ๐Ÿ“ฆ Deployment Artifacts (๋ฐฐํฌ ์•„ํ‹ฐํŒฉํŠธ ๊ทœ๊ฒฉ)
64
 
65
+ 1. `model_dti_fp16.baar3`: Zero-Copy ๋ฉ”๋ชจ๋ฆฌ ๋งคํ•‘ ๊ธฐ๋ฐ˜ ๊ณ ์† ์ถ”๋ก  ์ปค๋„ (1.8 MiB)
66
+ 2. `model_dti_q8.baar3`: ๋ชจ๋ฐ”์ผ/์—ฃ์ง€ ์ดˆ์ €์šฉ๋Ÿ‰ 8๋น„ํŠธ ๋Œ€์นญ ์–‘์žํ™” ๋ฐ”์ด๋„ˆ๋ฆฌ (0.86 MiB)
67
+ 3. `model_dti.onnx`: ์›น ๋ธŒ๋ผ์šฐ์ €(WASM/WebGPU) ๋ฐ ๋ฐฑ์—”๋“œ ํ†ตํ•ฉ์šฉ ONNX ๋Ÿฐํƒ€์ž„ ๊ทธ๋ž˜ํ”„
68
+ 4. `model.safetensors`: PyTorch ํ‘œ์ค€ ๊ฐ€์ค‘์น˜ ํŒŒ์ผ
69
+ 5. `vocab.json`: 20๊ฐœ ์•„๋ฏธ๋…ธ์‚ฐ ๋ฐ ๋ถ„์ž SMILES ํ† ํฐ ์ธ๋ฑ์Šค ์‚ฌ์ „
70
+ 6. `dti_test_evaluation_report.png`: Parity Plot, Residuals, ROC-PR Curve, Throughput 4ํŒจ๋„ ์ข…ํ•ฉ ํ•™์ˆ  ๊ฒ€์ฆ ๋ฆฌํฌํŠธ
71
 
72
  ---
73
 
74
+ ## ๐Ÿ“„ License & Commercial Terms (์—„๊ฒฉํ•œ ์ „๋ฉด ์œ ๋ฃŒ ๋ผ์ด์„ ์Šค ์ •์ฑ…)
75
+
76
+ โš ๏ธ **๋ณธ ๋ชจ๋ธ์€ ํ•™์ˆ  ์—ฐ๊ตฌ์™€ ์ƒ์—…์  ์ด์šฉ ๋ชจ๋‘ ์œ ๋ฃŒ ๋ผ์ด์„ ์Šค ๊ณ„์•ฝ ์ฒด๊ฒฐ์ด ํ•„์ˆ˜์ ์ธ ์ „๋ฉด ์œ ๋ฃŒ(Proprietary Paid) ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค.**
77
 
78
+ ### 1. Mandatory Paid License (์—ฐ๊ตฌยทํ•™์ˆ  ๋ชฉ์ ์„ ํฌํ•จํ•œ ์ „๋ฉด ์œ ๋ฃŒ ๊ณ„์•ฝ ํ•„์ˆ˜)
79
+ - **No Free Usage (๋ฌด๋ฃŒ ์ด์šฉ ๋ถˆ๊ฐ€)**:
80
+ This model is proprietary technology. **Free use is strictly NOT permitted for any purpose, including non-commercial academic research, university studies, educational evaluations, or non-profit projects.**
81
+ ๋ณธ ๋ชจ๋ธ์€ ๋…์  ๊ธฐ์ˆ  ์ž์‚ฐ์œผ๋กœ, **๋น„์˜๋ฆฌ ํ•™์ˆ  ์—ฐ๊ตฌ, ๋Œ€ํ•™ ๋ฐ ๊ต์œก ๊ธฐ๊ด€์˜ ์‹œํ—˜ ํ‰๊ฐ€, ๋…ผ๋ฌธ ์ž‘์„ฑ, ์—ฐ๊ตฌ์†Œ ํ”„๋กœ์ ํŠธ๋ฅผ ํฌํ•จํ•œ ์ผ์ฒด์˜ ๋ฌด๋ฃŒ ์ด์šฉ์ด ์—„๊ฒฉํžˆ ๊ธˆ์ง€**๋ฉ๋‹ˆ๋‹ค.
82
+ - **Academic Research License (์—ฐ๊ตฌ์šฉ ์œ ๋ฃŒ ๋ผ์ด์„ ์Šค)**:
83
+ Academic institutions, laboratories, and researchers must purchase an official Academic Research License prior to downloading, reproducing, fine-tuning, or executing this model.
84
+ ๋Œ€ํ•™ ์—ฐ๊ตฌ์†Œ, ํ•™์ˆ  ๋‹จ์ฒด ๋ฐ ๊ฐœ์ธ ์—ฐ๊ตฌ์ž๊ฐ€ ๋ณธ ๋ชจ๋ธ์„ ๋‹ค์šด๋กœ๋“œ, ์žฌํ˜„, ํŒŒ์ธํŠœ๋‹, ๊ฐ€์ƒ ์Šคํฌ๋ฆฌ๋‹ ์—ฐ๊ตฌ์— ์‚ฌ์šฉํ•˜๊ณ ์ž ํ•˜๋Š” ๊ฒฝ์šฐ์—๋„ ๋ฐ˜๋“œ์‹œ ์‚ฌ์ „์— ์—ฐ๊ตฌ์šฉ ์œ ๋ฃŒ ๋ผ์ด์„ ์Šค๋ฅผ ๋ฐœ๊ธ‰๋ฐ›์œผ์…”์•ผ ํ•ฉ๋‹ˆ๋‹ค.
85
 
86
+ ### 2. Commercial Enterprise Licensing (๊ธฐ์—… ์ƒ์šฉํ™” ๋ฐ ์‹ ์•ฝ ํŒŒ์ดํ”„๋ผ์ธ ๋„์ž…)
87
+ - **Biotech & Pharma Deployment (์ œ์•ฝยท๋ฐ”์ด์˜ค ๊ธฐ์—… ๋„์ž…)**:
88
+ Any pharmaceutical company, biotech startup, CRO, or commercial entity integrating this model into virtual screening pipelines, drug candidate discovery, or commercial APIs must acquire an Enterprise Commercial License.
89
+ ์‹ ์•ฝ ๊ฐœ๋ฐœ ํŒŒ์ดํ”„๋ผ์ธ, ๊ฐ€์ƒ ์Šคํฌ๋ฆฌ๋‹ ์†”๋ฃจ์…˜, ์œ ๋ฃŒ API ์„œ๋น„์Šค ๋ฐ ํ”Œ๋žซํผ์— ๋ณธ ์—”์ง„์„ ํƒ‘์žฌํ•˜๊ณ ์ž ํ•˜๋Š” ๊ธฐ์—…์€ ๊ธฐ์—…์šฉ ์ƒ์šฉ ๋ผ์ด์„ ์Šค๋ฅผ ์ฒด๊ฒฐํ•ด์•ผ ํ•ฉ๋‹ˆ๋‹ค.
90
+ - **๋ผ์ด์„ ์Šค ๊ฒฌ์  ๋ฐ ๋ผ์ด์„ ์Šค ๋ฐœ๊ธ‰ ๋ฌธ์˜ (License Inquiries)**: [admin@099.kr](mailto:admin@099.kr)
91
  - **๊ณต์‹ ์›น์‚ฌ์ดํŠธ (Official Website)**: [https://baar.uk/model/](https://baar.uk/model/)
92
 
93
  ---
94
 
95
+ ## โš ๏ธ Operational Notes (๊ฐ€์ƒ ์Šคํฌ๋ฆฌ๋‹ ํŒŒ์ดํ”„๋ผ์ธ ๊ฐ€์ด๋“œ)
96
 
97
+ - **Hierarchical Screening Cascade (๋‹จ๊ณ„์  ์Šคํฌ๋ฆฌ๋‹ ๊ถŒ์žฅ)**:
98
+ ์ˆ˜๋ฐฑ๋งŒ ๊ฐœ ์ด์ƒ์˜ ๋Œ€๊ทœ๋ชจ ํ™”ํ•ฉ๋ฌผ ๋ผ์ด๋ธŒ๋Ÿฌ๋ฆฌ(ZINC, Enamine ๋“ฑ) ํƒ์ƒ‰ ์‹œ, 1์ฐจ๋กœ ๋ณธ ์ดˆ๊ณ ์† ์—”์ง„(`BAAR3-drug-dti`)์„ ํ†ตํ•ด ์ƒ์œ„ 1%์˜ ์œ ํšจ ๊ฒฐํ•ฉ ํ›„๋ณด(pKd โ‰ฅ 7.0)๋ฅผ ์ดˆ๋‹จ์‹œ๊ฐ„์— ํ•„ํ„ฐ๋งํ•œ ํ›„, 2์ฐจ ์ •๋ฐ€ ๋ถ„์ž ๋„ํ‚น(AutoDock/Schrรถdinger)์œผ๋กœ ์—ฐ๊ณ„ํ•˜๋Š” ๊ณ„์ธต์  ํŒŒ์ดํ”„๋ผ์ธ ๊ตฌ์„ฑ์„ ์ ๊ทน ๊ถŒ์žฅํ•ฉ๋‹ˆ๋‹ค.
99
+ - **Sequence Length Truncation (์ž…๋ ฅ ๊ทœ๊ฒฉ)**:
100
+ ๋‹จ๋ฐฑ์งˆ ์„œ์—ด ์ตœ๋Œ€ 600 ์•„๋ฏธ๋…ธ์‚ฐ, ์•ฝ๋ฌผ SMILES ์ตœ๋Œ€ 120์ž๋กœ ์‚ฌ์ „ ํ† ํฌ๋‚˜์ด์ง•๋˜์–ด ์—ฐ์‚ฐ ํšจ์œจ์„ ๊ทน๋Œ€ํ™”ํ•ฉ๋‹ˆ๋‹ค.
101
+ - **Client-Side Screening (๋ณด์•ˆ ๊ฐ•ํ™”)**:
102
+ ๋™๋ด‰๋œ ONNX ๋ฐ `.baar3` ํฌ๋งท์„ ํ™œ์šฉํ•˜๋ฉด, ๋น„๊ณต๊ฐœ ํ›„๋ณด ๋ฌผ์งˆ SMILES ๋ฐ์ดํ„ฐ๋ฅผ ์™ธ๋ถ€ ํด๋ผ์šฐ๋“œ๋กœ ์ „์†กํ•˜์ง€ ์•Š๊ณ  ์‚ฌ๋‚ด ๋กœ์ปฌ ๋ธŒ๋ผ์šฐ์ €๋‚˜ ๋…๋ฆฝ๋œ ๋ณด์•ˆ ์—ฃ์ง€ ํ™˜๊ฒฝ์—์„œ ์•ˆ์ „ํ•˜๊ฒŒ ์Šคํฌ๋ฆฌ๋‹ํ•  ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.
103
 
104
  ---
105
 
106
+ ## ๐Ÿ’ผ Opportunities & Contact (์ฑ„์šฉ ์ œ์•ˆ ๋ฐ ๊ธฐ์ˆ  ํ˜‘๋ ฅ)
107
 
108
+ This project demonstrates practical competency in designing ultra-lightweight bioinformatics neural architectures, high-throughput in silico virtual screening pipelines, and hardware-optimized zero-copy deployment formats (`.baar3`, ONNX).
109
 
110
+ I am actively seeking **AI Engineering / Computational Biology Research opportunities, senior recruitment offers, and technical partnerships**.
111
 
112
  - **๊ณต์‹ ์›น์‚ฌ์ดํŠธ (Official Website)**: [https://baar.uk/model/](https://baar.uk/model/)
113
+ - **์—ฐ๊ตฌ ๋ฐ ๊ธฐ์—… ์œ ๋ฃŒ ๋ผ์ด์„ ์Šค ๋ฌธ์˜ (Paid Licensing)**: [admin@099.kr](mailto:admin@099.kr)
114
  - **์ฑ„์šฉ ๋ฐ ํฌ์ง€์…˜ ์ œ์•ˆ (Recruitment & Hiring)**: [admin@099.kr](mailto:admin@099.kr)
115
+ - **์‹ ์•ฝ AI ๊ณต๋™ ์—ฐ๊ตฌ ๋ฐ ๊ธฐ์ˆ  ์ œํœด (Partnerships)**: [admin@099.kr](mailto:admin@099.kr)
116
 
117
+ *์ˆ˜์–ต ์›๋Œ€์˜ ํด๋ผ์šฐ๋“œ GPU ์ธํ”„๋ผ ์—†์ด๋„ ์ผ๋ฐ˜ ์—ฃ์ง€ ๋ฐ ๋ธŒ๋ผ์šฐ์ €์—์„œ ์ดˆ๋‹น ์ˆ˜์ฒœ ๊ฐœ์˜ ์•ฝ๋ฌผ-๋‹จ๋ฐฑ์งˆ ๊ฒฐํ•ฉ์„ ์‹ค์‹œ๊ฐ„ ํŒ๋ณ„ํ•˜๋Š” ์ดˆ๊ฒฝ๋Ÿ‰ยท๊ณ ํšจ์œจ ๋ฐ”์ด์˜ค AI ์•„ํ‚คํ…์ฒ˜๋ฅผ ์ง์ ‘ ์„ค๊ณ„ํ•˜๊ณ  ์ตœ์ ํ™” ๋ฐฐํฌํ•˜๋Š” AI ์—”์ง€๋‹ˆ์–ด์ž…๋‹ˆ๋‹ค. ์ •๊ทœ์ง ํฌ์ง€์…˜ ์ œ์•ˆ ๋ฐ ๋ผ์ด์„ ์Šค ๋„์ž… ๋…ผ์˜๋ฅผ ํ™˜์˜ํ•ฉ๋‹ˆ๋‹ค.*