Articles

개의 글 articles

• 고정Pinned

  🎉KISA·SK쉴더스와 공동 제작한 「AI 보안 위협 대응 매뉴얼」 배포

  정보보호의 날을 맞아 KISA·SK쉴더스와 공동 제작한 'AI 보안 위협 대응 매뉴얼'이 배포되었습니다.

  김호기 교수• 3 min read • July 8, 2026 • news ai-security ai-safety security
• 고정Pinned

  🎉AI Security Threat Mitigation Manual Released with KISA and SK Shieldus

  On Information Security Day, the 'AI Security Threat Mitigation Manual' co-developed with KISA and SK Shieldus was released.

  Prof. Hoki Kim• 3 min read • July 8, 2026 • news ai-security ai-safety security
• 고정Pinned
  ICML 2026

  🎉중앙대학교 산업보안학과 김호기 교수 연구진, ICML 2026 논문 3편 채택

  AI 안전성·거버넌스·최적화 안정성 분야 논문 3편이 ICML 2026에 동시 채택

  김호기 교수• 2 min read • May 8, 2026 • news icml ai-safety news
• 고정Pinned
  ICML 2026

  🎉Prof. Hoki Kim's Research Team Has Three Papers Accepted to ICML 2026

  Three papers spanning AI safety, AI governance, and optimization stability accepted simultaneously to ICML 2026.

  Prof. Hoki Kim• 3 min read • May 8, 2026 • news icml ai-safety news
• 고정Pinned

  ✏️인공지능 위협과 신뢰성

  본 연구실이 제안하는 인공지능 위협의 두 층위(내재적 위협, 외재적 위협)와 신뢰성을 확보하기 위한 핵심 요소 및 국내외 규제 동향

  김호기 교수• 11 min read • March 1, 2026 • lecture-note trustworthy-ai trust security privacy explainability
• 고정Pinned

  ✏️AI Threat and Trustworthiness

  The two layers of AI threats that our lab proposes (intrinsic and extrinsic), and the key elements and regulations needed to make AI trustworthy

  Prof. Hoki Kim• 14 min read • March 1, 2026 • lecture-note trustworthy-ai trust security privacy explainability
• arXiv 2026

  🎉CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios

  연구실 논문 소개: LLM 에이전트의 공격 선택 편향(attack-selection bias) 벤치마크

  김호기 교수• 8 min read • June 11, 2026 • lab-paper llm-agent cybersecurity security
• arXiv 2026

  🎉CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios

  Attack-selection bias of LLM agents and the recent research paper from our lab

  Prof. Hoki Kim• 10 min read • June 11, 2026 • lab-paper llm-agent cybersecurity security
• ICML 2026

  🎉Stability Analysis of Sharpness-Aware Minimization

  연구실 논문 소개: 인공지능 일반화

  김호기 교수• 9 min read • May 7, 2026 • lab-paper flatness sharpness-aware-minimization security
• ICML 2026

  🎉Stability Analysis of Sharpness-Aware Minimization

  Generalization and the recent research paper from our lab

  Prof. Hoki Kim• 10 min read • May 7, 2026 • lab-paper generalization flatness generalization
• ICML 2026

  🎉Proactive Defense Benchmark Against Deepfake Generation

  연구실 논문 소개: 딥페이크 사전적 방어

  김호기 교수• 8 min read • May 7, 2026 • lab-paper deepfake proactive-defense deepfake
• ICML 2026

  🎉Proactive Defense Benchmark Against Deepfake Generation

  Proactive deepfake defense and the recent research paper from our lab

  Prof. Hoki Kim• 9 min read • May 7, 2026 • lab-paper deepfake proactive-defense deepfake
• ICML 2026

  🎉Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation Models

  연구실 논문 소개: 오픈웨이트 모델 거버넌스

  김호기 교수• 9 min read • May 7, 2026 • lab-paper ai-governance model-cards ai-governance
• ICML 2026

  🎉Position: Current Model Cards Are Insufficient for Downstream Governance of Open-Weight Foundation Models

  Open-weight model governance and the recent research paper from our lab

  Prof. Hoki Kim• 10 min read • May 7, 2026 • lab-paper ai-governance model-cards ai-governance

• 📖Adversarial Training for Free!

  Adversarial Robustness 논문 세미나 자료

  송예훈 연구원• 10 min read • April 25, 2026 • lab-seminar adversarial-attack adversarial-training security

• 📖Adversarial Training for Free!

  Adversarial Robustness Paper Seminar Materials

  Yehun Song• 13 min read • April 25, 2026 • lab-seminar adversarial-attack adversarial-training security

• 📖Adversarial Examples Are Not Bugs, They Are Features

  Adversarial Robustness 논문 세미나 자료

  최대승 연구원• 16 min read • April 25, 2026 • lab-seminar adversarial-examples non-robust-features security

• 📖Adversarial Examples Are Not Bugs, They Are Features

  Adversarial Robustness Paper Seminar Materials reinterpreting adversarial examples as non-robust features learned from data.

  Daeseung Choi• 22 min read • April 25, 2026 • lab-seminar adversarial-examples non-robust-features security

• 📖Theoretically Principled Trade-off between Robustness and Accuracy

  Adversarial Robustness 논문 세미나 자료

  김재성, 송예훈, 최대승 연구원• 13 min read • April 11, 2026 • lab-seminar adversarial-attack adversarial-robustness security

• 📖Theoretically Principled Trade-off between Robustness and Accuracy

  Adversarial Robustness Paper Seminar Materials

  Jaeseong Kim, Yehun Song, Daeseung Choi• 16 min read • April 11, 2026 • lab-seminar adversarial-attack adversarial-robustness security

• 📖Robustness May Be at Odds with Accuracy

  Adversarial Robustness 논문 세미나 자료

  송예훈 연구원• 9 min read • April 11, 2026 • lab-seminar adversarial-robustness accuracy-tradeoff security

• 📖Robustness May Be at Odds with Accuracy

  Adversarial Robustness Paper Seminar Materials

  Yehun Song• 11 min read • April 11, 2026 • lab-seminar adversarial-robustness accuracy-tradeoff security

• 📖Code Review: Adversarial Attacks and Defenses

  torchattacks · MAIR 라이브러리 기반 적대적 공격·방어 기법 코드 리뷰

  김재성, 송예훈, 최대승 연구원• 26 min read • April 11, 2026 • lab-seminar adversarial-attack adversarial-training security

• 📖Code Review: Adversarial Attacks and Defenses

  Line-by-line PyTorch walkthrough of torchattacks and MAIR implementations of adversarial attacks and defenses.

  Jaeseong Kim, Yehun Song, Daeseung Choi• 30 min read • April 11, 2026 • lab-seminar adversarial-attack adversarial-training security

• 📖Towards Evaluating the Robustness of Neural Networks

  Adversarial Robustness 논문 세미나 자료

  최대승 연구원• 13 min read • April 4, 2026 • lab-seminar adversarial-examples carlini-wagner security

• 📖Towards Evaluating the Robustness of Neural Networks

  C&W attacks expose that defensive distillation only masked existing attack weaknesses, redefining how adversarial robustness is evaluated.

  Daeseung Choi• 17 min read • April 4, 2026 • lab-seminar adversarial-examples carlini-wagner security

• 📖Obfuscated Gradients Give a False Sense of Security

  Adversarial Robustness 논문 세미나 자료

  김재성 연구원• 9 min read • April 4, 2026 • lab-seminar adversarial-attack circumventing-defenses security

• 📖Obfuscated Gradients Give a False Sense of Security

  Adversarial Robustness Paper Seminar Materials

  Researcher Jaeseong Kim• 12 min read • April 4, 2026 • lab-seminar adversarial-attack circumventing-defenses security

• 📖Adversarial Examples in the Physical World

  Adversarial Robustness 논문 세미나 자료

  최대승 연구원• 13 min read • March 28, 2026 • lab-seminar adversarial-examples physical-attacks security

• 📖Adversarial Examples in the Physical World

  Adversarial Robustness Paper Seminar Material

  Researcher Daeseung Choi• 16 min read • March 28, 2026 • lab-seminar adversarial-examples physical-attacks security

• 📖Towards Deep Learning Models Resistant to Adversarial Attacks

  Adversarial Robustness 논문 세미나 자료

  송예훈 연구원• 7 min read • March 27, 2026 • lab-seminar adversarial-attack robust-optimization security

• 📖Towards Deep Learning Models Resistant to Adversarial Attacks

  Adversarial Robustness paper seminar material

  Researcher Yehun Song• 8 min read • March 27, 2026 • lab-seminar adversarial-attack robust-optimization security

• 📖Intriguing Properties of Neural Networks

  Adversarial Robustness 논문 세미나 자료

  김재성 연구원• 11 min read • March 20, 2026 • lab-seminar adversarial-examples l-bfgs security

• 📖Intriguing Properties of Neural Networks

  Adversarial Robustness Paper Seminar Material

  Researcher Jaeseong Kim• 13 min read • March 20, 2026 • lab-seminar adversarial-examples l-bfgs security

• 📖Explaining and Harnessing Adversarial Examples

  Adversarial Robustness 논문 세미나 자료

  송예훈 연구원• 6 min read • March 20, 2026 • lab-seminar adversarial-attack fgsm security

• 📖Explaining and Harnessing Adversarial Examples

  Adversarial Robustness paper seminar material

  Researcher Yehun Song• 7 min read • March 20, 2026 • lab-seminar adversarial-attack fgsm security
• IEEE TII 2026 · Top 5%

  🎉중앙대학교 산업보안학과 김호기 교수 연구진, 상위 5% SCI 저널 게재

  산업 AI 환경에서의 머신 언러닝 연구 성과 소개

  김호기 교수• 2 min read • March 11, 2026 • news machine-unlearning privacy machine-unlearning
• IEEE TII 2026 · Top 5%

  🎉Prof. Hoki Kim's Research Team Publishes in Top 5% SCI Journal

  Introduction to machine unlearning research in industrial AI environments

  Prof. Hoki Kim• 3 min read • March 11, 2026 • news machine-unlearning privacy machine-unlearning
• IEEE TII 2026 · Top 5%

  🎉Adversarial Retain-Free Unlearning for Bearing Prognostics and Health Management

  머신 언러닝과 최근 연구실 논문 소개

  윤채원 연구원, 이지용 연구원, 김호기 교수• 10 min read • February 28, 2026 • lab-paper machine-unlearning adversarial-learning machine-unlearning
• IEEE TII 2026 · Top 5%

  🎉Adversarial Retain-Free Unlearning for Bearing Prognostics and Health Management

  Machine Unlearning and the recent research paper from our lab

  Researcher Chaewon Yoon, Researcher Jiyoung Lee, Prof. Hoki Kim• 12 min read • February 28, 2026 • lab-paper machine-unlearning adversarial-learning machine-unlearning

• 📖BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems

  LLM Cyber-Attack Bias Benchmark 논문 세미나 자료

  이지용 연구원• 9 min read • January 20, 2026 • lab-seminar AI-agent bug-bounty security

• 📖BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems

  LLM Cyber-Attack Bias Benchmark paper seminar material

  Researcher Jiyoung Lee• 12 min read • January 20, 2026 • lab-seminar AI-agent bug-bounty security

• 📖CYBENCH: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

  거대 언어 모델 사이버 공격 편향 벤치마크(LLM Cyber-Attack Bias Benchmark) 논문 세미나 자료

  주성용 연구원• 12 min read • January 12, 2026 • lab-seminar llm cyber-attack security

• 📖CYBENCH: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models

  LLM Cyber-Attack Bias Benchmark paper seminar material

  Researcher Seongyong Ju• 14 min read • January 12, 2026 • lab-seminar llm cyber-attack security

• 🎉‘2025 SW·AI Tech Fair’ 우수성과 발표대회 최우수상

  연구실 공모전 및 대회 수상

  김호기 교수• 2 min read • November 18, 2025 • award award

• 🎉Grand Prize at the '2025 SW·AI Tech Fair' Outstanding Achievement Presentation

  Lab competition and award achievement

  Prof. Hoki Kim• 3 min read • November 18, 2025 • award english award
• NeurIPS 2025

  🎉중앙대학교 산업보안학과 김호기 교수 논문, 세계 최고 인공지능 학회 채택

  머신 언러닝과 최근 연구실 논문 소개

  김호기 교수• 2 min read • October 22, 2025 • news machine-unlearning privacy machine-unlearning
• NeurIPS 2025

  🎉Prof. Hoki Kim's Paper Accepted at World's Top AI Conference

  Introduction to machine unlearning and recent lab research paper

  Prof. Hoki Kim• 2 min read • October 22, 2025 • news machine-unlearning privacy machine-unlearning
• NeurIPS 2025

  🎉Unlearning-Aware Minimization

  머신 언러닝과 최근 연구실 논문 소개

  김호기 교수• 9 min read • October 22, 2025 • lab-paper machine-unlearning privacy machine-unlearning
• NeurIPS 2025

  🎉Unlearning-Aware Minimization

  Machine Unlearning and the recent research paper from our lab

  Prof. Hoki Kim• 10 min read • October 22, 2025 • lab-paper machine-unlearning privacy machine-unlearning

• 📖Extracting Robust Models with Uncertain Examples

  Model Stealing and Application 논문 세미나 자료

  최대승 연구원• 14 min read • August 21, 2025 • lab-seminar best robustness-extraction privacy

• 📖Extracting Robust Models with Uncertain Examples

  Model Stealing and Application paper seminar material

  Researcher Daeseung Choi• 17 min read • August 21, 2025 • lab-seminar best robustness-extraction privacy

• 📖Perturbing Inputs to Prevent Model Stealing

  Model Stealing and Application 논문 세미나 자료

  김민철 연구원• 6 min read • August 14, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Perturbing Inputs to Prevent Model Stealing

  Model Stealing and Application paper seminar material

  Researcher Mincheol Kim• 7 min read • August 14, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Preventing Neural Network Weight Stealing via Network Obfuscation

  Model Stealing and Application 논문 세미나 자료

  김재성 연구원• 10 min read • August 5, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Preventing Neural Network Weight Stealing via Network Obfuscation

  Model Stealing and Application paper seminar material

  Researcher Jaeseong Kim• 12 min read • August 5, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Practical Black-Box Attacks Against Machine Learning

  Model Stealing and Application 논문 세미나 자료

  최대승 연구원• 16 min read • August 5, 2025 • lab-seminar papernot blackbox privacy

• 📖Practical Black-Box Attacks Against Machine Learning

  Model Stealing and Application paper seminar material

  Researcher Daeseung Choi• 19 min read • August 5, 2025 • lab-seminar papernot blackbox privacy

• 📖High Accuracy and High Fidelity Extraction of Neural Networks

  Model Stealing and Application 논문 세미나 자료

  최대승 연구원• 14 min read • August 5, 2025 • lab-seminar functionally-equivalent fidelity privacy

• 📖High Accuracy and High Fidelity Extraction of Neural Networks

  Model Stealing and Application paper seminar material

  Researcher Daeseung Choi• 17 min read • August 5, 2025 • lab-seminar functionally-equivalent fidelity privacy

• 📖Hiding CNN Parameters with Guided Grad-CAM

  Model Stealing and Application 논문 세미나 자료

  김재성 연구원• 8 min read • August 5, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Hiding CNN Parameters with Guided Grad-CAM

  Model Stealing and Application paper seminar material

  Researcher Jaeseong Kim• 10 min read • August 5, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks

  Model Stealing and Application 논문 세미나 자료

  김민철 연구원• 11 min read • July 31, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks

  Model Stealing and Application paper seminar materials

  Researcher Mincheol Kim• 12 min read • July 31, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Data-Free Model Extraction

  Model Stealing and Application 논문 세미나 자료

  김재성 연구원• 13 min read • July 31, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Data-Free Model Extraction

  Model Stealing and Application paper seminar materials

  Researcher Jaeseong Kim• 16 min read • July 31, 2025 • lab-seminar model-stealing model-extract privacy

• 📖PRADA: Protecting Against DNN Model Stealing Attacks

  Model Stealing and Application 논문 세미나 자료

  최대승 연구원• 12 min read • July 29, 2025 • lab-seminar detecting-extraction query-distribution privacy

• 📖PRADA: Protecting Against DNN Model Stealing Attacks

  Model Stealing and Application paper seminar materials

  Researcher Daeseung Choi• 15 min read • July 29, 2025 • lab-seminar detecting-extraction query-distribution privacy

• 📖Towards Reverse-Engineering Black-Box Neural Networks

  Model Stealing and Application 논문 세미나 자료

  김재성 연구원• 15 min read • July 24, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Towards Reverse-Engineering Black-Box Neural Networks

  Model Stealing and Application paper seminar materials

  Researcher Jaeseong Kim• 18 min read • July 24, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Knockoff Nets: Stealing Functionality of Black-Box Models

  Model Stealing and Application 논문 세미나 자료

  김민철 연구원• 10 min read • July 24, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Knockoff Nets: Stealing Functionality of Black-Box Models

  Model Stealing and Application paper seminar materials

  Researcher Mincheol Kim• 12 min read • July 24, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Stealing Hyperparameters in Machine Learning

  Model Stealing and Application 논문 세미나 자료

  최대승 연구원• 13 min read • July 17, 2025 • lab-seminar hyperparameter-stealing mlaas privacy

• 📖Stealing Hyperparameters in Machine Learning

  Model Stealing and Application paper seminar materials

  Researcher Daeseung Choi• 15 min read • July 17, 2025 • lab-seminar hyperparameter-stealing mlaas privacy

• 📖Stealing Machine Learning Models via Prediction APIs

  Model Stealing and Application 논문 세미나 자료

  김민철 연구원• 16 min read • July 17, 2025 • lab-seminar model-stealing model-extract privacy

• 📖Stealing Machine Learning Models via Prediction APIs

  Model Stealing and Application paper seminar materials

  Researcher Mincheol Kim• 18 min read • July 17, 2025 • lab-seminar model-stealing model-extract privacy
• CVPR 2025 Workshop

  🎉CaddieSet: A Golf Swing Dataset with Human Joint Features and Ball Information

  연구실 공동 연구 소개

  김호기 교수• 2 min read • June 5, 2025 • lab-paper interpretability golf explainability
• CVPR 2025 Workshop

  🎉CaddieSet: A Golf Swing Dataset with Human Joint Features and Ball Information

  Introduction to collaborative research from our lab

  Prof. Hoki Kim• 3 min read • June 5, 2025 • lab-paper interpretability golf explainability
• Applied Economics Letters 2025

  🎉Explaining Determinants of Bank Failure Prediction via Neural Additive Model

  연구실 논문 소개: 인공지능 설명성

  박민영 연구원, 이지용 연구원• 12 min read • March 15, 2025 • lab-paper post-hoc neural-additive-model explainability
• Applied Economics Letters 2025

  🎉Explaining Determinants of Bank Failure Prediction via Neural Additive Model

  Lab paper introduction: AI explainability

  Researcher Minyoung Park, Researcher Jiyoung Lee• 14 min read • March 15, 2025 • lab-paper post-hoc neural-additive-model explainability
• EAAI 2024 · Top 10%

  🎉Evaluating Practical Adversarial Robustness of Fault Diagnosis Systems via Spectrogram-Aware Ensemble Method

  연구실 논문 소개: 인공지능 강건성

  이지용 연구원, 윤채원 연구원• 10 min read • March 12, 2025 • lab-paper adversarial-attack fault-diagnosis-system security
• EAAI 2024 · Top 10%

  🎉Evaluating Practical Adversarial Robustness of Fault Diagnosis Systems via Spectrogram-Aware Ensemble Method

  Lab paper introduction: AI robustness

  Researcher Jiyoung Lee, Researcher Chaewon Yoon• 12 min read • March 12, 2025 • lab-paper adversarial-attack fault-diagnosis-system security

• 📖Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement

  머신언러닝(Machine Unlearning) 논문 세미나 자료

  윤채원 연구원• 11 min read • March 4, 2025 • lab-seminar machine-unlearning steepest-descent privacy

• 📖Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement

  Machine Unlearning paper seminar material

  Researcher Chaewon Yoon• 13 min read • March 4, 2025 • lab-seminar machine-unlearning steepest-descent privacy

• 📖Towards Unbounded Machine Unlearning

  머신언러닝(Machine Unlearning) 논문 세미나 자료

  이지용 연구원• 8 min read • March 4, 2025 • lab-seminar machine-unlearning scrub privacy

• 📖Towards Unbounded Machine Unlearning

  Machine Unlearning paper seminar material

  Researcher Jiyoung Lee• 10 min read • March 4, 2025 • lab-seminar machine-unlearning scrub privacy

• 📖Approximate Data Deletion from Machine Learning Models

  머신언러닝(Machine Unlearning) 논문 세미나 자료

  박민영 연구원• 9 min read • February 25, 2025 • lab-seminar machine-unlearning pru privacy

• 📖Approximate Data Deletion from Machine Learning Models

  Machine Unlearning paper seminar material

  Researcher Minyoung Park• 10 min read • February 25, 2025 • lab-seminar machine-unlearning pru privacy

• 📖SalUn: Empowering Machine Unlearning via Gradient-Based Weight Saliency in Both Image Classification and Generation

  머신언러닝(Machine Unlearning) 논문 세미나 자료

  윤채원 연구원• 9 min read • February 18, 2025 • lab-seminar machine-unlearning salun privacy

• 📖SalUn: Empowering Machine Unlearning via Gradient-Based Weight Saliency in Both Image Classification and Generation

  Machine Unlearning paper seminar material

  Researcher Chaewon Yoon• 11 min read • February 18, 2025 • lab-seminar machine-unlearning salun privacy

• 📖Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models

  머신언러닝(Machine Unlearning) 논문 세미나 자료

  이지용 연구원• 10 min read • February 18, 2025 • lab-seminar machine-unlearning diffusion-model privacy

• 📖Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models

  Machine Unlearning paper seminar material

  Researcher Jiyoung Lee• 13 min read • February 18, 2025 • lab-seminar machine-unlearning diffusion-model privacy

• 📖Machine Unlearning of Features and Labels

  머신언러닝(Machine Unlearning) 논문 세미나 자료

  박민영 연구원• 11 min read • February 18, 2025 • lab-seminar machine-unlearning second-order privacy

• 📖Machine Unlearning of Features and Labels

  Machine Unlearning paper seminar material

  Researcher Minyoung Park• 13 min read • February 18, 2025 • lab-seminar machine-unlearning second-order privacy

• 📖Amnesiac Machine Learning

  머신언러닝(Machine Unlearning) 논문 세미나 자료

  이지용 연구원• 13 min read • February 6, 2025 • lab-seminar machine-unlearning amnesiac privacy

• 📖Amnesiac Machine Learning

  Machine Unlearning paper seminar material

  Researcher Jiyoung Lee• 14 min read • February 6, 2025 • lab-seminar machine-unlearning amnesiac privacy

• 📖Evaluating Machine Unlearning via Epistemic Uncertainty

  머신언러닝(Machine Unlearning) 논문 세미나 자료

  윤채원 연구원• 5 min read • February 4, 2025 • lab-seminar machine-unlearning epistemic privacy

• 📖Evaluating Machine Unlearning via Epistemic Uncertainty

  Machine Unlearning paper seminar material

  Researcher Chaewon Yoon• 6 min read • February 4, 2025 • lab-seminar machine-unlearning epistemic privacy
• NeurIPS 2024

  🎉Are Self-Attentions Effective for Time Series Forecasting?

  연구실 논문 소개: 인공지능 설명성

  김호기 교수• 7 min read • October 1, 2024 • lab-paper self-attention time-series explainability
• NeurIPS 2024

  🎉Are Self-Attentions Effective for Time Series Forecasting?

  Lab paper introduction: AI explainability

  Prof. Hoki Kim• 8 min read • October 1, 2024 • lab-paper self-attention time-series explainability

• ✏️신뢰할 수 있는 인공지능의 핵심 요소와 기술적 과제

  신뢰할 수 있는 인공지능의 개념 및 연구실의 주요 기술 소개

  김호기 교수• 8 min read • September 1, 2024 • lecture-note trustworthy-ai trust security privacy explainability

• ✏️Key Elements and Technical Challenges of Trustworthy AI

  Concepts of trustworthy AI and introduction to our lab's key technologies

  Prof. Hoki Kim• 9 min read • September 1, 2024 • lecture-note trustworthy-ai trust security privacy explainability

• ✏️인공지능 규제와 신뢰성

  국제·국내 인공지능 관련 규제와 인공지능 신뢰성

  김호기 교수• 10 min read • September 1, 2024 • lecture-note regulation act security privacy explainability

• ✏️AI Regulations and Trustworthiness

  International and domestic AI-related regulations and AI trustworthiness

  Prof. Hoki Kim• 13 min read • September 1, 2024 • lecture-note regulation act security privacy explainability
• NeurIPS 2023

  🎉Fantastic Robustness Measures: The Secrets of Robust Generalization

  연구실 논문 소개: 인공지능 강건성

  김호기 교수• 13 min read • July 1, 2024 • lab-paper adversarial-robustness adversarial-attack security
• NeurIPS 2023

  🎉Fantastic Robustness Measures: The Secrets of Robust Generalization

  Adversarial robustness and the recent research paper from our lab

  Prof. Hoki Kim• 14 min read • July 1, 2024 • lab-paper adversarial-robustness adversarial-attack security

검색 결과가 없습니다.No matching articles.