Tuning without Peeking: Provable Privacy and Generalization Bounds for LLM Post-Training
Authors: Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud | Published: 2025-07-02
Graph Representation-based Model Poisoning on Federated LLMs in CyberEdge Networks
Authors: Hanlin Cai, Haofan Dong, Houtianfu Wang, Kai Li, Ozgur B. Akan | Published: 2025-07-02
説明可能なAI
AIの判断根拠を理解するための技術である説明可能なAI（XAI）に関する概要や関連研究の動向などについて解説します。XAIは、AIモデルがどのように判断や予測を行ったのか、その根拠や理由を人間が理解できる形で説明できるAI技術や仕組みを指します。本記事を読むことで、XAIの概要や研究の最新動向、課題、今後の方向性について理解を深めることができます。
A Privacy-Preserving Indoor Localization System based on Hierarchical Federated Learning
Authors: Masood Jan, Wafa Njima, Xun Zhang | Published: 2025-07-02
SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
Authors: Beitao Chen, Xinyu Lyu, Lianli Gao, Jingkuan Song, Heng Tao Shen | Published: 2025-07-02
ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks
Authors: Zhiyao Ren, Siyuan Liang, Aishan Liu, Dacheng Tao | Published: 2025-07-02
Gaze3P: Gaze-Based Prediction of User-Perceived Privacy
Authors: Mayar Elfares, Pascal Reisert, Ralf Küsters, Andreas Bulling | Published: 2025-07-01 | Updated: 2025-09-10
Are AI-Generated Fixes Secure? Analyzing LLM and Agent Patches on SWE-bench
Authors: Amirali Sajadi, Kostadin Damevski, Preetha Chatterjee | Published: 2025-06-30 | Updated: 2025-07-24
AI Risk-Management Standards Profile for General-Purpose AI (GPAI) and Foundation Models
Authors: Anthony M. Barrett, Jessica Newman, Brandie Nonnecke, Nada Madkour, Dan Hendrycks, Evan R. Murphy, Krystal Jackson, Deepika Raman | Published: 2025-06-30
PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)
Authors: Gonzalo Mancera, Aythami Morales, Julian Fierrez, Ruben Tolosana, Alejandro Penna, Miguel Lopez-Duran, Francisco Jurado, Alvaro Ortigosa | Published: 2025-06-30 | Updated: 2025-07-09