Description

本日紹介した論文の一覧

• Browsing without Third-Party Cookies: What Do You See?
  http://arxiv.org/abs/2410.10775v1

• Denial-of-Service Poisoning Attacks against Large Language Models
  http://arxiv.org/abs/2410.10760v1

• Composability in Watermarking Schemes
  http://arxiv.org/abs/2410.10712v1

• Sharing without Showing: Secure Cloud Analytics with Trusted Execution
  Environments
  http://arxiv.org/abs/2410.10574v1

• Regularized Robustly Reliable Learners and Instance Targeted Attacks
  http://arxiv.org/abs/2410.10572v1

• Generalized Adversarial Code-Suggestions: Exploiting Contexts of
  LLM-based Code-Completion
  http://arxiv.org/abs/2410.10526v1

• Model-Based Differentially Private Knowledge Transfer for Large Language
  Models
  http://arxiv.org/abs/2410.10481v1

• On Calibration of LLM-based Guard Models for Reliable Content Moderation
  http://arxiv.org/abs/2410.10414v1

• Tighter Risk Bounds for Mixtures of Experts
  http://arxiv.org/abs/2410.10397v1

• Yuan: Research on the Concept of Digital World Analogue Scientific
  Infrastructure and Science Popularization Communication Based on Suzhou
  Gardens Pattern
  http://arxiv.org/abs/2410.10248v1

• Identity-Focused Inference and Extraction Attacks on Diffusion Models
  http://arxiv.org/abs/2410.10177v1

• BinSimDB: Benchmark Dataset Construction for Fine-Grained Binary Code
  Similarity Analysis
  http://arxiv.org/abs/2410.10163v1

• From x*y=k to Uniswap Hooks; A Comparative Review of Decentralized
  Exchanges (DEX)
  http://arxiv.org/abs/2410.10162v1

• Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on
  Resource-Constrained Devices
  http://arxiv.org/abs/2410.10128v1

• Evaluating of Machine Unlearning: Robustness Verification Without Prior
  Modifications
  http://arxiv.org/abs/2410.10120v1

• StegaINR4MIH: steganography by implicit neural representation for
  multi-image hiding
  http://arxiv.org/abs/2410.10117v1

• Mastering AI: Big Data, Deep Learning, and the Evolution of Large
  Language Models -- Blockchain and Applications
  http://arxiv.org/abs/2410.10110v1

• XAI-based Feature Selection for Improved Network Intrusion Detection
  Systems
  http://arxiv.org/abs/2410.10050v1

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。