Description

本日紹介した論文の一覧

• Auditing Private Prediction
  http://arxiv.org/abs/2402.09403v1

• Introduction to Physically Unclonable Fuctions: Properties and
  Applications
  http://arxiv.org/abs/2402.09386v1

• Pseudorandom Error-Correcting Codes
  http://arxiv.org/abs/2402.09370v1

• Copyright Traps for Large Language Models
  http://arxiv.org/abs/2402.09363v1

• Inferentialist Resource Semantics
  http://arxiv.org/abs/2402.09217v1

• Discovering Command and Control (C2) Channels on Tor and Public Networks
  Using Reinforcement Learning
  http://arxiv.org/abs/2402.09200v1

• Cyber Deception Reactive: TCP Stealth Redirection to On-Demand Honeypots
  http://arxiv.org/abs/2402.09191v1

• Rapid Adoption, Hidden Risks: The Dual Impact of Large Language Model
  Customization
  http://arxiv.org/abs/2402.09179v1

• Web 3.0 and Quantum Security: Long-Distance Free-Space QSDC for Global
  Web 3.0 Networks
  http://arxiv.org/abs/2402.09108v1

• FedSiKD: Clients Similarity and Knowledge Distillation: Addressing
  Non-i.i.d. and Constraints in Federated Learning
  http://arxiv.org/abs/2402.09095v1

• Unity is Strength: Enhancing Precision in Reentrancy Vulnerability
  Detection of Smart Contract Analysis Tools
  http://arxiv.org/abs/2402.09094v1

• Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit
  Clues
  http://arxiv.org/abs/2402.09091v1

• Detection Latencies of Anomaly Detectors: An Overlooked Perspective ?
  http://arxiv.org/abs/2402.09082v1

• Blind Deep-Learning-Based Image Watermarking Robust Against Geometric
  Transformations
  http://arxiv.org/abs/2402.09062v1

• I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of
  Transformers using Fully Homomorphic Encryption
  http://arxiv.org/abs/2402.09059v1

• Review-Incorporated Model-Agnostic Profile Injection Attacks on
  Recommender Systems
  http://arxiv.org/abs/2402.09023v1

• Detecting Adversarial Spectrum Attacks via Distance to Decision Boundary
  Statistics
  http://arxiv.org/abs/2402.08986v1

• SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware
  Decoding
  http://arxiv.org/abs/2402.08983v1

• OmniBOR: A System for Automatic, Verifiable Artifact Resolution across
  Software Supply Chains
  http://arxiv.org/abs/2402.08980v1

• Seagull: Privacy preserving network verification system
  http://arxiv.org/abs/2402.08956v1

• Teamwork Makes TEE Work: Open and Resilient Remote Attestation on
  Decentralized Trust
  http://arxiv.org/abs/2402.08908v1

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。