Skip to content
View 2betforyou's full-sized avatar

Block or report 2betforyou

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
2betforyou/README.md

Junyoung Park

Typing SVG

LLM Safety Evaluation Failure Observability Applied AI Systems

Portfolio Google Scholar Email

I study LLM safety and evaluation, with a focus on process-level diagnosis of instruction-following failures and refusal dynamics.

I am an undergraduate student at Chung-Ang University, pursuing Art and Technology with Cyber Security as a convergence major. My work asks when, where, and how LLM failures form before they appear in final outputs — the token-by-token process a final answer hides. I like projects that turn research questions into reproducible evaluation pipelines, diagnostic signals, and working systems.

Focus Areas

  • LLM safety and evaluation
  • Logit dynamics, refusal/compliance margins, and early-token behavior
  • Jailbreak and instruction-following failure analysis
  • Benchmark design, LLM-as-Judge evaluation, and automated experiment pipelines
  • Applied AI systems, privacy-aware ML, and retrieval-based reasoning

Research

Work Topic Status
Persona Attack: Incremental Memory Injection Jailbreak Attack against LLMs Multi-turn jailbreak evaluation Preprint (arXiv:2606.00150)
TLO: Observing failure before the final answer Process-level safety evaluation In progress
GraphRAG for traceable financial QA Retrieval-based reasoning Oral accepted, 2025
FinSec LLM post-training for grounded QA Domain post-training In progress

Selected Projects

Project Description
build-up Evidence-first local deep-research agent with an append-only knowledge vault.
Temporal_Logit_Observability Temporal analysis of LLM safety activation via logit-margin scores.
Persona_Attack Incremental memory injection jailbreak attack experiments against LLMs.
GraphRAG-Conference GraphRAG framework for Korean financial-security regulatory interpretation.
FinSec-LLM-PostTraining RAG and QLoRA post-training pipeline for Korean financial-security and regulatory QA.
SafeAI_Final Machine unlearning experiment on privacy, fairness, and eye-coordinate regression.
AutoValetParking Centralized autonomous valet parking simulation with reservation-based path planning.

Working Style

  • I prefer benchmark design and reproducible workflows over one-off results.
  • I keep model weights, private datasets, generated artifacts, and credentials out of public repositories.
  • I document assumptions around data, evaluation conditions, metrics, and compute constraints.
한국어 소개

저는 LLM의 안전성과 평가를 연구하며, 특히 지시 이행 실패와 거부(refusal) 동역학을 최종 출력이 아니라 생성 과정 단위에서 진단하는 데 초점을 둡니다.

중앙대학교 학부생으로 예술공학을 전공하고 사이버보안을 융합전공하고 있습니다. 관심의 중심은 "LLM의 실패가 최종 답변에 드러나기 전, 언제·어디서·어떻게 형성되는가" 입니다. 연구 질문을 재현 가능한 평가 파이프라인과 진단 신호, 그리고 실제로 동작하는 시스템으로 옮기는 작업을 선호합니다.

연구 주제

  • LLM 안전성과 평가
  • Logit 동역학, 거부/순응 마진, 초기 토큰 행동
  • Jailbreak 및 지시 이행 실패 분석
  • 벤치마크 설계, LLM-as-Judge 평가, 실험 자동화 파이프라인
  • 응용 AI 시스템, 프라이버시 보존 ML, 검색 기반 추론

작업 원칙

  • 일회성 결과보다 벤치마크 설계와 재현 가능한 워크플로를 우선합니다.
  • 모델 가중치, 비공개 데이터셋, 생성 산출물, 자격 증명은 공개 저장소에 두지 않습니다.
  • 데이터, 평가 조건, 지표, 연산 제약에 대한 가정을 명시적으로 기록합니다.

GitHub Snapshot

GitHub stats Top languages

Links

Popular repositories Loading

  1. Persona_Attack Persona_Attack Public

    Incremental memory injection jailbreak attack experiments against LLMs

    Python 1

  2. Temporal_Logit_Observability Temporal_Logit_Observability Public

    Temporal analysis of LLM safety activation via logit-margin scores.

    Python 1 1

  3. 2betforyou.github.io 2betforyou.github.io Public

    Personal academic portfolio website built with GitHub Pages.

    SCSS

  4. SafeAI_Proposal SafeAI_Proposal Public

    Eye-detection pipeline for privacy-preserving face anonymization

    Jupyter Notebook

  5. SafeAI_Final SafeAI_Final Public

    Machine unlearning experiment on privacy, fairness, and eye-coordinate regression.

    Jupyter Notebook

  6. AutoValetParking AutoValetParking Public

    Centralized autonomous valet parking simulation with reservation-based path planning

    Python