Description

本日紹介した論文の一覧

• Hiding Text in Large Language Models: Introducing Unconditional Token
  Forcing Confusion
  http://arxiv.org/abs/2406.02481v1

• Click Without Compromise: Online Advertising Measurement via Per User
  Differential Privacy
  http://arxiv.org/abs/2406.02463v1

• Fast and Secure Decentralized Optimistic Rollups Using Setchain
  http://arxiv.org/abs/2406.02316v1

• PuFace: Defending against Facial Cloaking Attacks for Facial Recognition
  Models
  http://arxiv.org/abs/2406.02253v1

• Layer-2 Arbitrage: An Empirical Analysis of Swap Dynamics and Price
  Disparities on Rollups
  http://arxiv.org/abs/2406.02172v1

• Almost linear time differentially private release of synthetic graphs
  http://arxiv.org/abs/2406.02156v1

• Optimality of Matrix Mechanism on $\ell_p^p$-metric
  http://arxiv.org/abs/2406.02140v1

• Advancing Generalized Transfer Attack with Initialization Derived
  Bilevel Optimization and Dynamic Sequence Truncation
  http://arxiv.org/abs/2406.02064v1

• Inference Attacks in Machine Learning as a Service: A Taxonomy, Review,
  and Promising Directions
  http://arxiv.org/abs/2406.02027v1

• ShadowBound: Efficient Heap Memory Protection Through Advanced Metadata
  Management and Customized Compiler Optimization
  http://arxiv.org/abs/2406.02023v1

• A Risk Estimation Study of Native Code Vulnerabilities in Android
  Applications
  http://arxiv.org/abs/2406.02011v1

• Efficiently Train ASR Models that Memorize Less and Perform Better with
  Per-core Clipping
  http://arxiv.org/abs/2406.02004v1

• Measure-Observe-Remeasure: An Interactive Paradigm for
  Differentially-Private Exploratory Analysis
  http://arxiv.org/abs/2406.01964v1

• Bileve: Securing Text Provenance in Large Language Models Against
  Spoofing with Bi-level Signature
  http://arxiv.org/abs/2406.01946v1

• Position-based Rogue Access Point Detection
  http://arxiv.org/abs/2406.01927v1

• Image steganography based on generative implicit neural representation
  http://arxiv.org/abs/2406.01918v1

• HoneyGPT: Breaking the Trilemma in Terminal Honeypots with Large
  Language Model
  http://arxiv.org/abs/2406.01882v1

• CR-UTP: Certified Robustness against Universal Text Perturbations
  http://arxiv.org/abs/2406.01873v1

• A Survey of Unikernel Security: Insights and Trends from a Quantitative
  Analysis
  http://arxiv.org/abs/2406.01872v1

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。