Description

本日紹介した論文の一覧

• Differentially Private Worst-group Risk Minimization
  http://arxiv.org/abs/2402.19437v1

• SoK: Exploring the Potential of Large Language Models for Improving
  Digital Forensic Investigation Efficiency
  http://arxiv.org/abs/2402.19366v1

• Watermark Stealing in Large Language Models
  http://arxiv.org/abs/2402.19361v1

• Unraveling Adversarial Examples against Speaker Identification --
  Techniques for Attack Detection and Victim Model Classification
  http://arxiv.org/abs/2402.19355v1

• Verification of Neural Networks' Global Robustness
  http://arxiv.org/abs/2402.19322v1

• Attacks Against Mobility Prediction in 5G Networks
  http://arxiv.org/abs/2402.19319v1

• Machine learning for modular multiplication
  http://arxiv.org/abs/2402.19254v1

• Trained Random Forests Completely Reveal your Dataset
  http://arxiv.org/abs/2402.19232v1

• PRSA: Prompt Reverse Stealing Attacks against Large Language Models
  http://arxiv.org/abs/2402.19200v1

• Rahmani Sort: A Novel Variant of Insertion Sort Algorithm with O(nlogn)
  Complexity
  http://arxiv.org/abs/2402.19107v1

• RobWE: Robust Watermark Embedding for Personalized Federated Learning
  Model Ownership Protection
  http://arxiv.org/abs/2402.19054v1

• A Deep-Learning Technique to Locate Cryptographic Operations in
  Side-Channel Traces
  http://arxiv.org/abs/2402.19037v1

• How to Train your Antivirus: RL-based Hardening through the
  Problem-Space
  http://arxiv.org/abs/2402.19027v1

• SPriFed-OMP: A Differentially Private Federated Learning Algorithm for
  Sparse Basis Recovery
  http://arxiv.org/abs/2402.19016v1

• Ruledger: Ensuring Execution Integrity in Trigger-Action IoT Platforms
  http://arxiv.org/abs/2402.19011v1

• Always be Pre-Training: Representation Learning for Network Intrusion
  Detection with GNNs
  http://arxiv.org/abs/2402.18986v1

• Privacy Management and Interface Design for a Smart House
  http://arxiv.org/abs/2402.18973v1

• Syntactic Ghost: An Imperceptible General-purpose Backdoor Attacks on
  Pre-trained Language Models
  http://arxiv.org/abs/2402.18945v1

• On the Convergence of Differentially-Private Fine-tuning: To Linearly
  Probe or to Fully Fine-tune?
  http://arxiv.org/abs/2402.18905v1

• CEBin: A Cost-Effective Framework for Large-Scale Binary Code Similarity
  Detection
  http://arxiv.org/abs/2402.18818v1

• MPAT: Building Robust Deep Neural Networks against Textual Adversarial
  Attacks
  http://arxiv.org/abs/2402.18792v1

• Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial
  Defense
  http://arxiv.org/abs/2402.18787v1

• CoMeT: Count-Min-Sketch-based Row Tracking to Mitigate RowHammer at Low
  Cost
  http://arxiv.org/abs/2402.18769v1

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。