Description

本日紹介した論文の一覧

• Cocoon: A System Architecture for Differentially Private Training with
  Correlated Noises
  http://arxiv.org/abs/2510.07304v1

• Security-Robustness Trade-offs in Diffusion Steganography: A Comparative
  Analysis of Pixel-Space and VAE-Based Architectures
  http://arxiv.org/abs/2510.07219v1

• Covert Quantum Learning: Privately and Verifiably Learning from Quantum
  Data
  http://arxiv.org/abs/2510.07193v1

• Exposing LLM User Privacy via Traffic Fingerprint Analysis: A Study of
  Privacy Risks in LLM Agent Interactions
  http://arxiv.org/abs/2510.07176v1

• A multi-layered embedded intrusion detection framework for programmable
  logic controllers
  http://arxiv.org/abs/2510.07171v1

• Spectral Graph Clustering under Differential Privacy: Balancing Privacy,
  Accuracy, and Efficiency
  http://arxiv.org/abs/2510.07136v1

• GNN-enhanced Traffic Anomaly Detection for Next-Generation SDN-Enabled
  Consumer Electronics
  http://arxiv.org/abs/2510.07109v1

• Pseudo-MDPs: A Novel Framework for Efficiently Optimizing Last Revealer
  Seed Manipulations in Blockchains
  http://arxiv.org/abs/2510.07080v1

• RedTWIZ: Diverse LLM Red Teaming via Adaptive Attack Planning
  http://arxiv.org/abs/2510.06994v1

• VelLMes: A high-interaction AI-based deception framework
  http://arxiv.org/abs/2510.06975v1

• I Can't Patch My OT Systems! A Look at CISA's KEVC Workarounds &
  Mitigations for OT
  http://arxiv.org/abs/2510.06951v1

• The Knowledge Complexity of Quantum Problems
  http://arxiv.org/abs/2510.06923v1

• Multi-hop Deep Joint Source-Channel Coding with Deep Hash Distillation
  for Semantically Aligned Image Retrieval
  http://arxiv.org/abs/2510.06868v1

• Exposing Citation Vulnerabilities in Generative Engines
  http://arxiv.org/abs/2510.06823v1

• Bionetta: Efficient Client-Side Zero-Knowledge Machine Learning Proving
  http://arxiv.org/abs/2510.06784v1

• Differentially Private Synthetic Text Generation for Retrieval-Augmented
  Generation (RAG)
  http://arxiv.org/abs/2510.06719v1

• Representation Gap of the Motzkin Monoid
  http://arxiv.org/abs/2510.06707v1

• Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial?
  http://arxiv.org/abs/2510.06692v1

• Distilling Lightweight Language Models for C/C++ Vulnerabilities
  http://arxiv.org/abs/2510.06645v1

• Unsupervised Backdoor Detection and Mitigation for Spiking Neural
  Networks
  http://arxiv.org/abs/2510.06629v1

• Code Agent can be an End-to-end System Hacker: Benchmarking Real-world
  Threats of Computer-use Agent
  http://arxiv.org/abs/2510.06607v1

• Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting
  via Zeroth-order Gradient Estimation
  http://arxiv.org/abs/2510.06605v1

• Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in
  LLM-Based Text Steganography
  http://arxiv.org/abs/2510.06565v1

• Benchmarking Fake Voice Detection in the Fake Voice Generation Arms Race
  http://arxiv.org/abs/2510.06544v1

• SpyChain: Multi-Vector Supply Chain Attacks on Small Satellite Systems
  http://arxiv.org/abs/2510.06535v1

• From Description to Detection: LLM based Extendable O-RAN Compliant
  Blind DoS Detection in 5G and Beyond
  http://arxiv.org/abs/2510.06530v1

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。