Description

本日紹介した論文の一覧

• Emerging Paradigms for Securing Federated Learning Systems
  http://arxiv.org/abs/2509.21147v1

• EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing
  Email Defense
  http://arxiv.org/abs/2509.21129v1

• PMark: Towards Robust and Distortion-free Semantic-level Watermarking
  with Channel Constraints
  http://arxiv.org/abs/2509.21057v1

• Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
  http://arxiv.org/abs/2509.21011v1

• Dual-Path Phishing Detection: Integrating Transformer-Based NLP with
  Structural URL Analysis
  http://arxiv.org/abs/2509.20972v1

• CTI Dataset Construction from Telegram
  http://arxiv.org/abs/2509.20943v1

• RLCracker: Exposing the Vulnerability of LLM Watermarks with Adaptive RL
  Attacks
  http://arxiv.org/abs/2509.20924v1

• A Generalized $χ_n$-Function
  http://arxiv.org/abs/2509.20880v1

• FlowXpert: Context-Aware Flow Embedding for Enhanced Traffic Detection
  in IoT Network
  http://arxiv.org/abs/2509.20861v1

• Security-aware Semantic-driven ISAC via Paired Adversarial Residual
  Networks
  http://arxiv.org/abs/2509.20835v1

• Intelligent Graybox Fuzzing via ATPG-Guided Seed Generation and
  Submodule Analysis
  http://arxiv.org/abs/2509.20808v1

• Fast Revocable Attribute-Based Encryption with Data Integrity for
  Internet of Things
  http://arxiv.org/abs/2509.20796v1

• ExpIDS: A Drift-adaptable Network Intrusion Detection System With
  Improved Explainability
  http://arxiv.org/abs/2509.20767v1

• Cryptographic Backdoor for Neural Networks: Boon and Bane
  http://arxiv.org/abs/2509.20714v1

• Average-Case Complexity of Quantum Stabilizer Decoding
  http://arxiv.org/abs/2509.20697v1

• Reliability Analysis of Fully Homomorphic Encryption Systems Under
  Memory Faults
  http://arxiv.org/abs/2509.20686v1

• Can Federated Learning Safeguard Private Data in LLM Training?
  Vulnerabilities, Attacks, and Defense Evaluation
  http://arxiv.org/abs/2509.20680v1

• A Framework for Rapidly Developing and Deploying Protection Against
  Large Language Model Attacks
  http://arxiv.org/abs/2509.20639v1

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。