Description

本日紹介した論文の一覧

• ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented
  Code Generation
  http://arxiv.org/abs/2509.07941v1

• Guided Reasoning in LLM-Driven Penetration Testing Using Structured
  Attack Trees
  http://arxiv.org/abs/2509.07939v1

• A Non-Monotonic Relationship: An Empirical Analysis of Hybrid Quantum
  Classifiers for Unseen Ransomware Detection
  http://arxiv.org/abs/2509.07924v1

• Inner-product Functional Encryption with Fine-grained Revocation for
  Flexible EHR Sharing
  http://arxiv.org/abs/2509.07804v1

• AgentSentinel: An End-to-End and Real-Time Security Defense Framework
  for Computer-Use Agents
  http://arxiv.org/abs/2509.07764v1

• Empirical Security Analysis of Software-based Fault Isolation through
  Controlled Fault Injection
  http://arxiv.org/abs/2509.07757v1

• Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for
  Medical Texts
  http://arxiv.org/abs/2509.07755v1

• Leveraging Digital Twin-as-a-Service Towards Continuous and Automated
  Cybersecurity Certification
  http://arxiv.org/abs/2509.07649v1

• Embedded Off-Switches for AI Compute
  http://arxiv.org/abs/2509.07637v1

• FlexEmu: Towards Flexible MCU Peripheral Emulation (Extended Version)
  http://arxiv.org/abs/2509.07615v1

• Enhanced cast-128 with adaptive s-box optimization via neural networks
  for image protection
  http://arxiv.org/abs/2509.07606v1

• PatchSeeker: Mapping NVD Records to their Vulnerability-fixing Commits
  with LLM Generated Commits and Embeddings
  http://arxiv.org/abs/2509.07540v1

• Extension of Spatial k-Anonymity: New Metrics for Assessing the
  Anonymity of Geomasked Data Considering Realistic Attack Scenarios
  http://arxiv.org/abs/2509.07505v1

• Backdoor Attacks and Defenses in Computer Vision Domain: A Survey
  http://arxiv.org/abs/2509.07504v1

• Biometric Bound Credentials for Age Verification
  http://arxiv.org/abs/2509.07465v1

• A Decade-long Landscape of Advanced Persistent Threats: Longitudinal
  Analysis and Global Trends
  http://arxiv.org/abs/2509.07457v1

• When Fine-Tuning is Not Enough: Lessons from HSAD on Hybrid and
  Adversarial Audio Spoof Detection
  http://arxiv.org/abs/2509.07323v1

• SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool
  Utilization Safety in LLMs
  http://arxiv.org/abs/2509.07315v1

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。