| OT |
https://oecd.ai/en/ai-principles |
| https://cleanlab.ai/tlm/ |
|
| https://arxiv.org/pdf/2307.02483.pdf |
|
| https://www.tta.or.kr/tta/selectBbsNttView.do?key=74&bbsNo=105&nttNo=13315&searchCtgry=&searchCnd=all&searchKrwd=&integrDeptCode=&pageIndex=1 |
|
| 1주차 - Fariness AI |
영상 : https://www.youtube.com/watch?v=wqXVIkdy52E |
| 논문 : https://arxiv.org/pdf/2302.08017v1.pdf |
|
| 블로그 : https://www.samsungsds.com/kr/insights/ai-fairness.html |
|
| 2주차 - Sustainability AI |
블로그 : https://hbr.org/2023/07/how-to-make-generative-ai-greener |
| 논문 : https://www.nature.com/articles/s41467-019-14108-y |
|
| 3주차 - Trustworthy AI |
논문 : https://arxiv.org/abs/2110.01167 |
| 협약 : https://oecd.ai/en/ai-principles |
|
| 영상 : https://youtu.be/kIiO4VSrivU?si=Kbc_EI-MYRSm5tNc |
|
| https://cleanlab.ai/tlm/ |
|
| https://www.copyright.or.kr/information-materials/publication/research-report/download.do?brdctsno=52591&brdctsfileno=22636 |
|
| 4주차 - 프로젝트 팀 빌딩 및 토의 |
영상 : https://www.youtube.com/watch?v=gn0Z_glYJ90 |
| detection model : https://huggingface.co/laiyer/deberta-v3-base-prompt-injection |
|
| 프롬프트 https://gandalf.lakera.ai/ |
|
| 5주차 - Jailbreaking w/ Prompts |
AntiGPT |
| 블로그 : https://www.lakera.ai/blog/jailbreaking-large-language-models-guide |
|
| Github : https://github.com/0xk1h0/ChatGPT_DAN 해당 논문 :https://arxiv.org/pdf/2308.03825.pdf |
|
| 논문 : https://arxiv.org/pdf/2311.05608.pdf |
|
| 6주차 - Fairness in Gen AI |
https://arxiv.org/abs/2107.07754 |
| https://arxiv.org/abs/2307.04138 |
|
| https://fra.europa.eu/sites/default/files/fra_uploads/fra-2019-data-quality-and-ai_en.pdf |
|
|
|
| 7주차 - Sustainability AI |
https://kpmg.com/kpmg-us/content/dam/kpmg/pdf/2023/genai_enrc_Sep26.pdf |
| 8주차 - Trustworthy Gen AI |
https://yunqing-me.github.io/AttackVLM/ |
| https://openreview.net/forum?id=plmBsXHxgR |
|
| 9주차 - 중간 리뷰/프로젝트 회의 |
|
| 10,11주차 - Gen AI project for avoiding toxicity |
영상 : https://www.youtube.com/watch?v=gn0Z_glYJ90 |
| 논문 : https://arxiv.org/pdf/2402.06900.pdf |
|
| Tutorial : https://www.youtube.com/watch?v=esMeEo4PQe4 |
|
| 12,13주차 - LLM trustworthy project |
https://arxiv.org/pdf/2212.08073.pdf |
| https://arxiv.org/pdf/2307.14539.pdf |
|
| https://python.langchain.com/docs/guides/safety/ |
|
| https://machine-learning-made-simple.medium.com/7-methods-to-secure-llm-apps-from-prompt-injections-and-jailbreaks-11987b274012 |
|
| https://labelerrors.com/ |
|
