Description

本日紹介した論文の一覧

• Self-adaptive Dataset Construction for Real-World Multimodal Safety
  Scenarios
  http://arxiv.org/abs/2509.04403v1

• An Empirical Study of Vulnerabilities in Python Packages and Their
  Detection
  http://arxiv.org/abs/2509.04260v1

• An Automated, Scalable Machine Learning Model Inversion Assessment
  Pipeline
  http://arxiv.org/abs/2509.04214v1

• KubeGuard: LLM-Assisted Kubernetes Hardening via Configuration Files and
  Runtime Logs Analysis
  http://arxiv.org/abs/2509.04191v1

• ECCFROG522PP: An Enhanced 522-bit Weierstrass Elliptic Curve
  http://arxiv.org/abs/2509.04097v1

• Revisiting Third-Party Library Detection: A Ground Truth Dataset and Its
  Implications Across Security Tasks
  http://arxiv.org/abs/2509.04091v1

• ICSLure: A Very High Interaction Honeynet for PLC-based Industrial
  Control Systems
  http://arxiv.org/abs/2509.04080v1

• Error Detection Schemes for Barrett Reduction of CT-BU on FPGA in Post
  Quantum Cryptography
  http://arxiv.org/abs/2509.04070v1

• Systematic Timing Leakage Analysis of NIST PQDSS Candidates: Tooling and
  Lessons Learned
  http://arxiv.org/abs/2509.04010v1

• NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language
  Models
  http://arxiv.org/abs/2509.03985v1

• LMAE4Eth: Generalizable and Robust Ethereum Fraud Detection by Exploring
  Transaction Semantics and Masked Graph Embedding
  http://arxiv.org/abs/2509.03939v1

• The Auth Shim: A Lightweight Architectural Pattern for Integrating
  Enterprise SSO with Standalone Open-Source Applications
  http://arxiv.org/abs/2509.03900v1

• ShieldMMU: Detecting and Defending against Controlled-Channel Attacks in
  Shielding Memory System
  http://arxiv.org/abs/2509.03879v1

• A Comprehensive Survey on Trustworthiness in Reasoning with Large
  Language Models
  http://arxiv.org/abs/2509.03871v1

• KGBERT4Eth: A Feature-Complete Transformer Powered by Knowledge Graph
  for Multi-Task Ethereum Fraud Detection
  http://arxiv.org/abs/2509.03860v1

• Rethinking Tamper-Evident Logging: A High-Performance, Co-Designed
  Auditing System
  http://arxiv.org/abs/2509.03821v1

• BIDO: A Unified Approach to Address Obfuscation and Concept Drift
  Challenges in Image-based Malware Detection
  http://arxiv.org/abs/2509.03807v1

• Peekaboo, I See Your Queries: Passive Attacks Against DSSE Via
  Intermittent Observations
  http://arxiv.org/abs/2509.03806v1

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。