Description

本日紹介した論文の一覧

• Defending Against Prompt Injection With a Few DefensiveTokens
  http://arxiv.org/abs/2507.07974v1

• EinHops: Einsum Notation for Expressive Homomorphic Operations on
  RNS-CKKS Tensors
  http://arxiv.org/abs/2507.07972v1

• KeyDroid: A Large-Scale Analysis of Secure Key Storage in Android Apps
  http://arxiv.org/abs/2507.07927v1

• Can Large Language Models Improve Phishing Defense? A Large-Scale
  Controlled Experiment on Warning Dialogue Explanations
  http://arxiv.org/abs/2507.07916v1

• The Trust Fabric: Decentralized Interoperability and Economic
  Coordination for the Agentic Web
  http://arxiv.org/abs/2507.07901v1

• Mitigating Watermark Stealing Attacks in Generative Models via Multi-Key
  Watermarking
  http://arxiv.org/abs/2507.07871v1

• Rainbow Artifacts from Electromagnetic Signal Injection Attacks on Image
  Sensors
  http://arxiv.org/abs/2507.07773v1

• GuardVal: Dynamic Large Language Model Jailbreak Evaluation for
  Comprehensive Safety Testing
  http://arxiv.org/abs/2507.07735v1

• RADAR: a Radio-based Analytics for Dynamic Association and Recognition
  of pseudonyms in VANETs
  http://arxiv.org/abs/2507.07732v1

• Temporal Unlearnable Examples: Preventing Personal Video Data from
  Unauthorized Exploitation by Object Tracking
  http://arxiv.org/abs/2507.07483v1

• May I have your Attention? Breaking Fine-Tuning based Prompt Injection
  Defenses using Architecture-Aware Attacks
  http://arxiv.org/abs/2507.07417v1

• Autonomous AI-based Cybersecurity Framework for Critical Infrastructure:
  Real-Time Threat Mitigation
  http://arxiv.org/abs/2507.07416v1

• Hybrid LLM-Enhanced Intrusion Detection for Zero-Day Threats in IoT
  Networks
  http://arxiv.org/abs/2507.07413v1

• Phishing Detection in the Gen-AI Era: Quantized LLMs vs Classical Models
  http://arxiv.org/abs/2507.07406v1

• Shuffling for Semantic Secrecy
  http://arxiv.org/abs/2507.07401v1

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。