Trustworthy Machine Learning Lab
Konkuk Univ.
Department of Computer Science & Engineering
Embedded Files
Join
2026년도 2학기 대학원생(석사/석박통합)을 모집하고 있습니다.
인공지능에서의 프라이버시, 보안, 신뢰성 등에 관심이 있는 학생은 swhong06@konkuk.ac.kr로 연락주세요.
Research Topics
본 연구실은 사람의 의도와 사회적 규범에 맞게 행동하는 신뢰성 인공지능을 목표로 아래와 같은 주제를 연구합니다.
Vision-Language-Action Model
신뢰할 수 있는 로봇 AI 학습
신뢰할 수 있는 로봇 AI 학습
Keyword: VLA, View-Invariant Representation, Action-Centric
자율 주행 모델에서의 설명 가능성
자율 주행 모델에서의 설명 가능성
Keyword: VLA, Autonomous Vehicle, XAI
General AI
AI 모델에 대한 적대적 공격
AI 모델에 대한 적대적 공격
Keyword: Adversarial Attack, Transfer Attack, Model Ensemble
AI의 공정성 & 설명 가능성
AI의 공정성 & 설명 가능성
Keyword: Fair & Explainable AI
Generative AI
사람의 의도를 반영한 생성형 AI 모델
사람의 의도를 반영한 생성형 AI 모델
Keyword: Reliable Generative AI, Constrained Generation
생성형 AI 모델에서의 저작권 문제 해결
생성형 AI 모델에서의 저작권 문제 해결
Keyword: Memorization, Generative AI, Copyright
News
[Mar. 2026] Our team has been selected to lead the 'Verifiable Privacy-Preserving Machine Unlearning' project, as part of 신진연구.
[Mar. 2026] Our paper about Efficient Fidelity Estimation for Quantum State has been accepted to Phyiscal Review A.
[Mar. 2026] Our paper about Communication using AI has been accepted to IEEE Wireless Communication Letters.
[Feb. 2026] Our paper about Efficient VLA Pretrainig has been released on arXiv.
[Jan. 2026] Prof. Hong delivered an invited talk on XAI at the Sejong University.
[Jan. 2026] Our Lab introduce a GPU server equipped with 2 X NVIDIA RTX Pro 6000 GPU. (198GB VRAM)
[Jan. 2026] Prof. Hong delivered an invited talk on generative AI and privacy at the National Institute for Mathematical Sciences.
[Nov. 2025] Our Lab have established a partnership with Theta Labs by signing an MOU.
[Nov. 2025] Our paper about Reliable Generative AI has been accepted to AAAI 2026 as an Oral Presentation.
[Nov. 2025] Our paper about Efficient Fidelity Estimation for Quantum State has been released on arXiv.
[Sep. 2025] Our paper about Reliable Communication using Generative AI has been accepted to AI4NextG@NeurIPSW 25 .
[Sep. 2025] Our paper about Enhancing Data Privacy in Generative AI has been accepted to NeurIPS 2025.
[Aug. 2025] Our team has been selected to lead the 'Coded Parallel Tensor Network Contraction for Robust and Efficient Quantum Circuit Simulation' project, as part of the 우수신진연구.
[Aug. 2025] Our team at Konkuk University has been selected for the 그룹연구인력양성 사업.
[Feb. 2025] Our paper about Explainable AI has been accepted to AAAI 2025.
Page updated
Google Sites
Report abuse