Description

本日紹介した論文の一覧

• Case Study: Neural Network Malware Detection Verification for Feature
  and Image Datasets
  http://arxiv.org/abs/2404.05703v1

• AI-Enabled System for Efficient and Effective Cyber Incident Detection
  and Response in Cloud Environments
  http://arxiv.org/abs/2404.05602v1

• Hook-in Privacy Techniques for gRPC-based Microservice Communication
  http://arxiv.org/abs/2404.05598v1

• Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data
  http://arxiv.org/abs/2404.05530v1

• Simplifying MBA Expression Using E-Graphs
  http://arxiv.org/abs/2404.05431v1

• SoK: Gradient Leakage in Federated Learning
  http://arxiv.org/abs/2404.05403v1

• Optimal Controller Realizations against False Data Injections in
  Cooperative Driving
  http://arxiv.org/abs/2404.05361v1

• Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized
  Smoothing
  http://arxiv.org/abs/2404.05350v1

• Reflected Search Poisoning for Illicit Promotion
  http://arxiv.org/abs/2404.05320v1

• Automated Attack Synthesis for Constant Product Market Makers
  http://arxiv.org/abs/2404.05297v1

• Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in
  Multimodal Large Language Model Security
  http://arxiv.org/abs/2404.05264v1

• A Note on the Common Haar State Model
  http://arxiv.org/abs/2404.05227v1

• Have You Merged My Model? On The Robustness of Large Language Model IP
  Protection Methods Against Model Merging
  http://arxiv.org/abs/2404.05188v1

• Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods
  http://arxiv.org/abs/2404.05159v1

• Enabling Privacy-Preserving Cyber Threat Detection with Federated
  Learning
  http://arxiv.org/abs/2404.05130v1

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。