Description

本日紹介した論文の一覧

• AUTOPSY: A Framework for Tackling Privacy Challenges in the Automotive
  Industry
  http://arxiv.org/abs/2507.16788v1

• When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning
  LLMs
  http://arxiv.org/abs/2507.16773v1

• LLMxCPG: Context-Aware Vulnerability Detection Through Code Property
  Graph-Guided Large Language Models
  http://arxiv.org/abs/2507.16585v1

• From Text to Actionable Intelligence: Automating STIX Entity and
  Relationship Extraction
  http://arxiv.org/abs/2507.16576v1

• Explainable Vulnerability Detection in C/C++ Using Edge-Aware Graph
  Attention Networks
  http://arxiv.org/abs/2507.16540v1

• Depth Gives a False Sense of Privacy: LLM Internal States Inversion
  http://arxiv.org/abs/2507.16372v1

• DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via
  Distribution Modeling
  http://arxiv.org/abs/2507.16329v1

• Towards Resilient Safety-driven Unlearning for Diffusion Models against
  Downstream Fine-tuning
  http://arxiv.org/abs/2507.16302v1

• Talking Like a Phisher: LLM-Based Attacks on Voice Phishing Classifiers
  http://arxiv.org/abs/2507.16291v1

• From Contracts to Code: Automating Smart Contract Generation with
  Multi-Level Finite State Machines
  http://arxiv.org/abs/2507.16276v1

• eX-NIDS: A Framework for Explainable Network Intrusion Detection
  Leveraging Large Language Models
  http://arxiv.org/abs/2507.16241v1

• Distilled Large Language Model in Confidential Computing Environment for
  System-on-Chip Design
  http://arxiv.org/abs/2507.16226v1

• LENS-DF: Deepfake Detection and Temporal Localization for Long-Form
  Noisy Speech
  http://arxiv.org/abs/2507.16220v1

• SVAgent: AI Agent for Hardware Security Verification Assertion
  http://arxiv.org/abs/2507.16203v1

• Pulse-Level Simulation of Crosstalk Attacks on Superconducting Quantum
  Hardware
  http://arxiv.org/abs/2507.16181v1

• Attacking interpretable NLP systems
  http://arxiv.org/abs/2507.16164v1

• DP2Guard: A Lightweight and Byzantine-Robust Privacy-Preserving
  Federated Learning Scheme for Industrial IoT
  http://arxiv.org/abs/2507.16134v1

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。