Description

本日紹介した論文の一覧

• Layer-Aware Representation Filtering: Purifying Finetuning Data to
  Preserve LLM Safety Alignment
  http://arxiv.org/abs/2507.18631v1

• Scout: Leveraging Large Language Models for Rapid Digital Evidence
  Discovery
  http://arxiv.org/abs/2507.18478v1

• Conformidade com os Requisitos Legais de Privacidade de Dados: Um Estudo
  sobre Técnicas de Anonimização
  http://arxiv.org/abs/2507.18360v1

• Regression-aware Continual Learning for Android Malware Detection
  http://arxiv.org/abs/2507.18313v1

• LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language
  Models
  http://arxiv.org/abs/2507.18302v1

• Scheduzz: Constraint-based Fuzz Driver Generation with Dual Scheduling
  http://arxiv.org/abs/2507.18289v1

• Auto-SGCR: Automated Generation of Smart Grid Cyber Range Using IEC
  61850 Standard Models
  http://arxiv.org/abs/2507.18249v1

• Information Security Based on LLM Approaches: A Review
  http://arxiv.org/abs/2507.18215v1

• An Improved ChaCha Algorithm Based on Quantum Random Number
  http://arxiv.org/abs/2507.18157v1

• Understanding the Supply Chain and Risks of Large Language Model
  Applications
  http://arxiv.org/abs/2507.18105v1

• PyPitfall: Dependency Chaos and Software Supply Chain Vulnerabilities in
  Python
  http://arxiv.org/abs/2507.18075v1

• RECALLED: An Unbounded Resource Consumption Attack on Large
  Vision-Language Models
  http://arxiv.org/abs/2507.18053v1

• Your ATs to Ts: MITRE ATT&CK Attack Technique to P-SSCRM Task Mapping
  http://arxiv.org/abs/2507.18037v1

• NWaaS: Nonintrusive Watermarking as a Service for X-to-Image DNN
  http://arxiv.org/abs/2507.18036v1

• Removing Box-Free Watermarks for Image-to-Image Models via Query-Based
  Reverse Engineering
  http://arxiv.org/abs/2507.18034v1

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。