ホーム > 佐久間 淳/ Sakuma, Jun

佐久間 淳

ALUMNI 2026年10月現在、筑波大学が主たる所属機関ではありません

Sakuma, Jun

東京科学大学 , 情報理工学院 , 教授
Institute of Science Tokyo , School of Computing , Professor

http://www.mdl.cs.tsukuba.ac.jp

  1. 1. Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG). Junki Mori; Kazuya Kakizaki; Taiki Miyagawa; Jun Sakuma
      ACL (Findings) 1216 (2026)
  2. 2. Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models. Ragib Amin Nihal; Rui Wen; Kazuhiro Nakadai; Jun Sakuma
      ACL (Findings) 22123 (2026)
  3. 3. When Benchmarks Leak: Inference-Time Decontamination for LLMs. Jianzhe Chai; Zhe Yu; Jun Sakuma
      ACL (1) 44743 (2026)
  4. 4. MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs. Rui Wen 0002; Mark Russinovich; Andrew Paverd; Jun SakumaAhmed Salem 0001
      CoRR abs/2605.15172: (2026) Semantic Scholar
  5. 5. Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills. Chia-Yi Hsu; Chi-Yu Li 0001; Chun-Ying Huang; Jun Sakuma
      CoRR abs/2605.29354: (2026) Semantic Scholar
  6. 6. Adversarial Beats: Feasibility Study of Spoofed Arrhythmia in Automated Electrocardiogram Diagnosis. Taiga Ono; Takeshi Sugawara 0001; Jun Sakuma; Tatsuya Mori 0003
      ACM Trans. Cyber Phys. Syst. 10: 12 (2026) Semantic Scholar
  7. 7. When Benchmarks Leak: Inference-Time Decontamination for LLMs. Jianzhe Chai; Yu Zhe; Jun Sakuma
      CoRR abs/2601.19334: (2026) Semantic Scholar
  8. 8. One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs. Yixin Tan; Zhe Yu; Jun Sakuma
      CoRR abs/2512.14751: (2025) Semantic Scholar
  9. 9. Disrupting Model Merging: A Parameter-Level Defense without Sacrificing Accuracy. Junhao Wei; Yu Zhe; Jun Sakuma
      ICCV 17698 (2025) Semantic Scholar
  10. 10. Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models. Haochuan Xu; Yun Sing Koh; Shuhuai Huang; Zirun Zhou (+2 著者) Jingfeng Zhang
      CoRR abs/2510.13237: (2025) Semantic Scholar
  11. 11. Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models. Ragib Amin Nihal; Rui Wen; Kazuhiro Nakadai; Jun Sakuma
      CoRR abs/2510.08859: (2025) Semantic Scholar
  12. 12. Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG). Junki Mori; Kazuya Kakizaki; Taiki Miyagawa; Jun Sakuma
      CoRR abs/2510.06719: (2025) Semantic Scholar
  13. 13. Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability. Shojiro Yamabe; Jun Sakuma
      CoRR abs/2510.00565: (2025) Semantic Scholar
  14. 14. Explainable Classifier for Malignant Lymphoma Subtyping via Cell Graph and Image Fusion. Daiki Nishiyama; Hiroaki Miyoshi; Noriaki Hashimoto; Koichi Ohshima (+2 著者) Jun Sakuma
      Medical Image Computing and Computer Assisted Intervention - MICCAI 2025 - 28th International Conference 320 (2025)
  15. 15. Remembering Transformer for Continual Learning. Yuwei Sun; Ippei Fujisawa; Arthur Juliani; Jun SakumaRyota Kanai
      IJCNN 1 (2025) Semantic Scholar
  16. 16. Weakening Prediction Confidence Makes Backdoors Strengthened: A Strong Textual Backdoor Attack on Prefix-tuning. Yixin Tan; Haoyu Zhang; Jun Sakuma
      IJCNN 1 (2025) Semantic Scholar
  17. 17. Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift. Mitsuhiro Fujikawa; Youhei Akimoto; Jun Sakuma; Kazuto Fukuchi
      International Conference on Artificial Intelligence and Statistics(AISTATS) 226 (2025)
  18. 18. Explainable Classifier for Malignant Lymphoma Subtyping via Cell Graph and Image Fusion. Daiki Nishiyama; Hiroaki Miyoshi; Noriaki Hashimoto; Koichi Ohshima (+2 著者) Jun Sakuma
      CoRR abs/2503.00925: (2025) Semantic Scholar
  19. 19. Data Poisoning Attacks to Locally Differentially Private Range Query Protocols. Ting-Wei Liao; Chih-Hsun Lin; Yu-Lin Tsai; Takao Murakami (+3 著者) Hiroaki Kikuchi
      CoRR abs/2503.03454: (2025) Semantic Scholar
  20. 20. Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy. Junhao Wei; Yu Zhe; Jun Sakuma
      CoRR abs/2503.07661: (2025) Semantic Scholar
1 2 3 … 15
  1. 1. Privacy-Preserving Local Search for the Traveling Salesman Problem Jun, Sakuma; Shigenobu, Kobayashi
    Intech 2010年12月
  2. 2. 進化技術ハンドブック 佐久間淳
    近代科学社 2010年1月
  3. 3. 交叉オペレータによる高次元分布推定とその最適化・モデル推定への応用 佐久間, 淳
    2003年3月
  1. 1. モデル化誤差に頑健な Max-Min Off-Policy Actor-Critic 田邊, 拓実; 福地, 一斗; 佐久間, 淳; 秋本, 洋平
    2022年度人工知能学会全国大会（第36回） 2022年6月14日
  2. 2. Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation Tran, Thien Q; Fukuchi, Kazuto; Akimoto, Yohei; Sakuma, Jun
    36th AAAI Conference on Artificial Intelligence 2022年2月22日
  3. 3. Adaptive Scenario Subset Selection for Minimax Black-Box Continuous Optimization Miyagi, Atsuhiro; Fukuchi, Kazuto; Sakuma, Jun; Akimoto, Yohei
    GECCO '21 2021年7月10日
  4. 4. Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Function Morinaga, Daiki; Fukuchi, Kazuto; Sakuma, Jun; Akimoto, Yohei
    GECCO '21 2021年7月10日
  5. 5. Level Generation for Angry Birds with Sequential VAE and Latent Variable Evolution Tanabe, Takumi; Fukuchi, Kazuto; Sakuma, Jun; Akimoto, Yohei
    GECCO '21 2021年7月10日
  6. 6. Sequential Variational Autoencoderを用いたAngry Birdsのステージ生成 田邊, 拓実; 福地, 一斗; 佐久間, 淳; 秋本, 洋平
    2021年度人工知能学会全国大会（第35回） 2021年6月8日
  7. 7. 深層生成モデルによる弱パレート解集合の近似 江戸, 陽向; 濱田, 直希; 福地, 一斗; 佐久間, 淳; 秋本, 洋平
    2021年度人工知能学会全国大会（第35回） 2021年6月8日
  8. 8. 複数の損失関数を用いた深層生成モデルの訓練と制約付きブラックボックス最適化への適用 阪本, 直気; 佐藤, 怜; 福地, 一斗; 佐久間, 淳; 秋本, 洋平
    2021年度人工知能学会全国大会（第35回） 2021年6月8日
  9. 9. (1+1)-Evolution Strategyの凸二次関数における収束速度の導出 森永, 大貴; 福地, 一斗; 佐久間, 淳; 秋本, 洋平
    2021年度人工知能学会全国大会（第35回） 2021年6月8日
  10. 10. AdvantageNAS: Efficient Neural Architecture Search with Credit Assignment Sato, Rei; Sakuma, Jun; Akimoto, Yohei
    Proceedings of the AAAI Conference on Artificial Intelligence 2021年2月2日
  11. 11. Deep Generative Model for Non-convex Constraint Handling Sakamoto, Naoki; Semmatsu, Eiji; Fukuchi, Kazuto; Sakuma, Jun; Akimoto, Youhei
    Genetic and Evolutionary Computation Conference (GECCO) 2020年7月8日
  12. 12. Statistically Significant Pattern Mining with Ordinal Utility Tran, Thien Q; Fukuchi, Kazuto; Akimoto, Yohei; Sakuma, Jun
    KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2020年7月6日
  13. 13. Generate (non-software) Bugs to Fool Classifiers Yakura, Hiromu; Akimoto, Yohei; Sakuma, Jun
    Thirty-Fourth AAAI Conference on Artificial Intelligence, New York, New York, USA, February 7-12, 2020 2020年2月7日
  14. 14. Identification of nine genes as novel susceptibility loci for early-onset ischemic stroke, intracerebral hemorrhage, or subarachnoid hemorrhage Yamase, Y; Horibe, H; Kato, K; Oguri, M; Fujimaki, T; Hibino, T; Kondo, T; Sakuma, J; Takeuchi, I; Murohara, T; Yasukochi, I; Yamada, Y
    Congress of the European-Society-of-Cardiology (ESC) / World Congress of Cardiology 2019年8月31日
  15. 15. Seasonal-adjustment Based Feature Selection Method for Predicting Epidemic with Large-scale Search Engine Logs Tran, Thien Q; Sakuma, Jun
    25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD) 2019年8月4日
  16. 16. Robust Watermarking of Neural Network with Exponential Weighting Namba, Ryota; Sakuma, Jun
    ACM Asia Conference on Computer and Communications Security (Asia CCS) 2019年7月9日
  17. 17. AI for Security, Security for AI Sakuma,Jun
    LINE x Intertrust Security Summit 2019 2019年5月20日 LINE corp. 招待有り
  18. 18. 離散分布におけるシャノンエントロピー型のAdditive汎関数のミニマックス最適推定 福地, 一斗; 佐久間, 淳
    第41回情報理論とその応用シンポジウム (SITA2018) 2018年12月18日 電子情報通信学会 基礎・境界ソサイエティ 情報理論とその応用サブソサイエティ
  19. 19. More Practical Privacy-Preserving Machine Learning as A Service via Efficient Secure Matrix Multiplication 佐久間, 淳
    The 6th Workshop on Encrypted Computing & Applied Homomorphic Cryptography 2018年10月19日
  20. 20. Outsourced Private Function Evaluation with Privacy Policy Enforcement Kunihiro, Noboru; Lu, Wen-Jie; Nishide, Takashi; Sakuma, Jun
    IEEE TrustCom2018 2018年8月
1 2 3

 1,623 total views