Description

本日紹介した論文の一覧

• An Algorithmic Pipeline for GDPR-Compliant Healthcare Data
  Anonymisation: Moving Toward Standardisation
  http://arxiv.org/abs/2506.02942v1

• When Blockchain Meets Crawlers: Real-time Market Analytics in Solana NFT
  Markets
  http://arxiv.org/abs/2506.02892v1

• ATAG: AI-Agent Application Threat Assessment with Attack Graphs
  http://arxiv.org/abs/2506.02859v1

• Rethinking Machine Unlearning in Image Generation Models
  http://arxiv.org/abs/2506.02761v1

• Privacy Leaks by Adversaries: Adversarial Iterations for Membership
  Inference Attack
  http://arxiv.org/abs/2506.02711v1

• Poster: FedBlockParadox -- A Framework for Simulating and Securing
  Decentralized Federated Learning
  http://arxiv.org/abs/2506.02679v1

• Decentralized COVID-19 Health System Leveraging Blockchain
  http://arxiv.org/abs/2506.02674v1

• Poster: libdebug, Build Your Own Debugger for a Better (Hello) World
  http://arxiv.org/abs/2506.02667v1

• Tarallo: Evading Behavioral Malware Detectors in the Problem Space
  http://arxiv.org/abs/2506.02660v1

• CyberGym: Evaluating AI Agents' Cybersecurity Capabilities with
  Real-World Vulnerabilities at Scale
  http://arxiv.org/abs/2506.02548v1

• Attention Knows Whom to Trust: Attention-based Trust Management for LLM
  Multi-Agent Systems
  http://arxiv.org/abs/2506.02546v1

• BitBypass: A New Direction in Jailbreaking Aligned Large Language Models
  with Bitstream Camouflage
  http://arxiv.org/abs/2506.02479v1

• VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
  http://arxiv.org/abs/2506.02456v1

• A Review of Various Datasets for Machine Learning Algorithm-Based
  Intrusion Detection System: Advances and Challenges
  http://arxiv.org/abs/2506.02438v1

• MISLEADER: Defending against Model Extraction with Ensembles of
  Distilled Models
  http://arxiv.org/abs/2506.02362v1

なお、ポッドキャスト内で紹介する内容は、各論文の概要を日本語で解説したもので、論文概要の著作権は論文著者に帰属します。