Description

本日紹介した論文の一覧

• Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting
  Technique
  http://arxiv.org/abs/2407.10887v1

• SLIP: Securing LLMs IP Using Weights Decomposition
  http://arxiv.org/abs/2407.10886v1

• Provable Robustness of (Graph) Neural Networks Against Data Poisoning
  and Backdoor Attacks
  http://arxiv.org/abs/2407.10867v1

• Enhancing Cyber Security through Predictive Analytics: Real-Time Threat
  Detection and Response
  http://arxiv.org/abs/2407.10864v1

• Wicked Oddities: Selectively Poisoning for Effective Clean-Label
  Backdoor Attacks
  http://arxiv.org/abs/2407.10825v1

• GHunter: Universal Prototype Pollution Gadgets in JavaScript Runtimes
  http://arxiv.org/abs/2407.10812v1

• TME-Box: Scalable In-Process Isolation through Intel TME-MK Memory
  Encryption
  http://arxiv.org/abs/2407.10740v1

• Mitigating Data Imbalance for Software Vulnerability Assessment: Does
  Data Augmentation Help?
  http://arxiv.org/abs/2407.10722v1

• MARTSIA: Safeguarding Data Confidentiality in Blockchain-Driven Process
  Execution
  http://arxiv.org/abs/2407.10684v1

• TripletViNet: Mitigating Misinformation Video Spread Across Platforms
  http://arxiv.org/abs/2407.10644v1

• The Medium is the Message: How Secure Messaging Apps Leak Sensitive Data
  to Push Notification Services
  http://arxiv.org/abs/2407.10589v1

• GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio
  Synthesis
  http://arxiv.org/abs/2407.10471v1

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。