Description

本日紹介した論文の一覧

• Improving Users' Passwords with DPAR: a Data-driven Password
  Recommendation System
  http://arxiv.org/abs/2406.03423v1

• CROSSCON: Cross-platform Open Security Stack for Connected Devices
  http://arxiv.org/abs/2406.03401v1

• Elliptic curves over Hasse pairs
  http://arxiv.org/abs/2406.03399v1

• How to Construct Quantum FHE, Generically
  http://arxiv.org/abs/2406.03379v1

• A Framework for Mapping Organisational Workforce Knowledge Profile in
  Cyber Security
  http://arxiv.org/abs/2406.03322v1

• Defending Large Language Models Against Attacks With Residual Stream
  Activation Analysis
  http://arxiv.org/abs/2406.03230v1

• Fuzzing Frameworks for Server-side Web Applications: A Survey
  http://arxiv.org/abs/2406.03208v1

• Graph Neural Network Explanations are Fragile
  http://arxiv.org/abs/2406.03193v1

• Ariadne: a Privacy-Preserving Communication Protocol
  http://arxiv.org/abs/2406.03187v1

• Reconstructing training data from document understanding models
  http://arxiv.org/abs/2406.03182v1

• ZeroPur: Succinct Training-Free Adversarial Purification
  http://arxiv.org/abs/2406.03143v1

• The Harder You Try, The Harder You Fail: The KeyTrap Denial-of-Service
  Algorithmic Complexity Attacks on DNSSEC
  http://arxiv.org/abs/2406.03133v1

• BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
  http://arxiv.org/abs/2406.03007v1

• PrE-Text: Training Language Models on Private Federated Data in the Age
  of LLMs
  http://arxiv.org/abs/2406.02958v1

• Nonlinear Transformations Against Unlearnable Datasets
  http://arxiv.org/abs/2406.02883v1

• DREW : Towards Robust Data Provenance by Leveraging Error-Controlled
  Watermarking
  http://arxiv.org/abs/2406.02836v1

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。