Description

本日紹介した論文の一覧

• How to evaluate control measures for LLM agents? A trajectory from today
  to superintelligence
  http://arxiv.org/abs/2504.05259v1

• Infinitely Divisible Noise for Differential Privacy: Nearly Optimal
  Error in the High $\varepsilon$ Regime
  http://arxiv.org/abs/2504.05202v1

• A Fast Multiplication Algorithm and RLWE-PLWE Equivalence for the
  Maximal Real Subfield of the $2^r p^s$-th Cyclotomic Field
  http://arxiv.org/abs/2504.05159v1

• Pr$εε$mpt: Sanitizing Sensitive Prompts for LLMs
  http://arxiv.org/abs/2504.05147v1

• Taming Double-Spending in Offline Payments with Reputation-Weighted Loan
  Networks
  http://arxiv.org/abs/2504.05143v1

• Hollow Victory: How Malicious Proposers Exploit Validator Incentives in
  Optimistic Rollup Dispute Games
  http://arxiv.org/abs/2504.05094v1

• Enhancing Smart Contract Vulnerability Detection in DApps Leveraging
  Fine-Tuned LLM
  http://arxiv.org/abs/2504.05006v1

• SmartBugBert: BERT-Enhanced Vulnerability Detection for Smart Contract
  Bytecode
  http://arxiv.org/abs/2504.05002v1

• Select Me! When You Need a Tool: A Black-box Text Attack on Tool
  Selection
  http://arxiv.org/abs/2504.04809v1

• Out of Sight, Still at Risk: The Lifecycle of Transitive Vulnerabilities
  in Maven
  http://arxiv.org/abs/2504.04803v1

• Enhancing Trust in AI Marketplaces: Evaluating On-Chain Verification of
  Personalized AI models using zk-SNARKs
  http://arxiv.org/abs/2504.04794v1

• Teaching Data Science Students to Sketch Privacy Designs through
  Heuristics (Extended Technical Report)
  http://arxiv.org/abs/2504.04734v1

• A High-Performance Curve25519 and Curve448 Unified Elliptic Curve
  Cryptography Accelerator
  http://arxiv.org/abs/2504.04731v1

• Are You Getting What You Pay For? Auditing Model Substitution in LLM
  APIs
  http://arxiv.org/abs/2504.04715v1

• Generative Large Language Model usage in Smart Contract Vulnerability
  Detection
  http://arxiv.org/abs/2504.04685v1

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。