Description

本日紹介した論文の一覧

• The Tail Tells All: Estimating Model-Level Membership Inference
  Vulnerability Without Reference Models
  http://arxiv.org/abs/2510.19773v1

• Under Pressure: Security Analysis and Process Impacts of a Commercial
  Smart Air Compressor
  http://arxiv.org/abs/2510.19772v1

• Exploring the Effect of DNN Depth on Adversarial Attacks in Network
  Intrusion Detection Systems
  http://arxiv.org/abs/2510.19761v1

• Unfair Mistakes on Social Media: How Demographic Characteristics
  influence Authorship Attribution
  http://arxiv.org/abs/2510.19708v1

• CircuitGuard: Mitigating LLM Memorization in RTL Code Generation Against
  IP Leakage
  http://arxiv.org/abs/2510.19676v1

• FidelityGPT: Correcting Decompilation Distortions with Retrieval
  Augmented Generation
  http://arxiv.org/abs/2510.19615v1

• Can You Trust What You See? Alpha Channel No-Box Attacks on Video Object
  Detection
  http://arxiv.org/abs/2510.19574v1

• Privacy-Preserving Spiking Neural Networks: A Deep Dive into Encryption
  Parameter Optimisation
  http://arxiv.org/abs/2510.19537v1

• Cross-Chain Sealed-Bid Auctions Using Confidential Compute Blockchains
  http://arxiv.org/abs/2510.19491v1

• AegisMCP: Online Graph Intrusion Detection for Tool-Augmented LLMs on
  Edge Devices
  http://arxiv.org/abs/2510.19462v1

• Transmitter Identification via Volterra Series Based Radio Frequency
  Fingerprint
  http://arxiv.org/abs/2510.19440v1

• Monitoring LLM-based Multi-Agent Systems Against Corruptions via Node
  Evaluation
  http://arxiv.org/abs/2510.19420v1

• From See to Shield: ML-Assisted Fine-Grained Access Control for Visual
  Data
  http://arxiv.org/abs/2510.19418v1

• Bytecode-centric Detection of Known-to-be-vulnerable Dependencies in
  Java Projects
  http://arxiv.org/abs/2510.19393v1

• A Probabilistic Computing Approach to the Closest Vector Problem for
  Lattice-Based Factoring
  http://arxiv.org/abs/2510.19390v1

• ConvXformer: Differentially Private Hybrid ConvNeXt-Transformer for
  Inertial Navigation
  http://arxiv.org/abs/2510.19352v1

• Authorization of Knowledge-base Agents in an Intent-based Management
  Function
  http://arxiv.org/abs/2510.19324v1

• Collaborative penetration testing suite for emerging generative AI
  algorithms
  http://arxiv.org/abs/2510.19303v1

• An Adaptive Intelligent Thermal-Aware Routing Protocol for Wireless Body
  Area Networks
  http://arxiv.org/abs/2510.19300v1

• Reliability and Resilience of AI-Driven Critical Network Infrastructure
  under Cyber-Physical Threats
  http://arxiv.org/abs/2510.19295v1

• An Empirical Study of Bitwise Operators Intuitiveness through
  Performance Metrics
  http://arxiv.org/abs/2510.19281v1

• LAPRAD: LLM-Assisted PRotocol Attack Discovery
  http://arxiv.org/abs/2510.19264v1

• Defending Against Prompt Injection with DataFilter
  http://arxiv.org/abs/2510.19207v1

• OpenGuardrails: An Open-Source Context-Aware AI Guardrails Platform
  http://arxiv.org/abs/2510.19169v1

• HAMLOCK: HArdware-Model LOgically Combined attacK
  http://arxiv.org/abs/2510.19145v1

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。