Description

本日紹介した論文の一覧

• The Learning Stabilizers with Noise problem
  http://arxiv.org/abs/2410.18953v1

• SafeBench: A Safety Evaluation Framework for Multimodal Large Language
  Models
  http://arxiv.org/abs/2410.18927v1

• Provably Robust Watermarks for Open-Source Language Models
  http://arxiv.org/abs/2410.18861v1

• PSY: Posterior Sampling Based Privacy Enhancer in Large Language Models
  http://arxiv.org/abs/2410.18824v1

• Robust Watermarking Using Generative Priors Against Image Editing: From
  Benchmarking to Advances
  http://arxiv.org/abs/2410.18775v1

• NIDS Neural Networks Using Sliding Time Window Data Processing with
  Trainable Activations and its Generalization Capability
  http://arxiv.org/abs/2410.18658v1

• Complexity Matters: Effective Dimensionality as a Measure for
  Adversarial Robustness
  http://arxiv.org/abs/2410.18556v1

• FirmRCA: Towards Post-Fuzzing Analysis on ARM Embedded Firmware with
  Efficient Event-based Fault Localization
  http://arxiv.org/abs/2410.18483v1

• RediSwap: MEV Redistribution Mechanism for CFMMs
  http://arxiv.org/abs/2410.18434v1

• Knowledge-Assisted Privacy Preserving in Semantic Communication
  http://arxiv.org/abs/2410.18418v1

• Enhancing Feature-Specific Data Protection via Bayesian Coordinate
  Differential Privacy
  http://arxiv.org/abs/2410.18404v1

• Faster Algorithms for User-Level Private Stochastic Convex Optimization
  http://arxiv.org/abs/2410.18391v1

• Harnessing PU Learning for Enhanced Cloud-based DDoS Detection: A
  Comparative Analysis
  http://arxiv.org/abs/2410.18380v1

• FedBaF: Federated Learning Aggregation Biased by a Foundation Model
  http://arxiv.org/abs/2410.18352v1

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。