Description

本日紹介した論文の一覧

• Correlated Privacy Mechanisms for Differentially Private Distributed
  Mean Estimation
  http://arxiv.org/abs/2407.03289v1

• Anomaly-based Framework for Detecting Power Overloading Cyberattacks in
  Smart Grid AMI
  http://arxiv.org/abs/2407.03264v1

• Reconsidering utility: unveiling the limitations of synthetic mobility
  data generation algorithms in real-life scenarios
  http://arxiv.org/abs/2407.03237v1

• Self-Evaluation as a Defense Against Adversarial Attacks on LLMs
  http://arxiv.org/abs/2407.03234v1

• SOS! Soft Prompt Attack Against Open-Source Large Language Models
  http://arxiv.org/abs/2407.03160v1

• Revisiting the Performance of Deep Learning-Based Vulnerability
  Detection on Realistic Datasets
  http://arxiv.org/abs/2407.03093v1

• Federated Learning for Zero-Day Attack Detection in 5G and Beyond V2X
  Networks
  http://arxiv.org/abs/2407.03070v1

• Identification of Device Dependencies Using Link Prediction
  http://arxiv.org/abs/2407.03019v1

• Zero-X: A Blockchain-Enabled Open-Set Federated Learning Framework for
  Zero-Day Attack Detection in IoV
  http://arxiv.org/abs/2407.02969v1

• ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary
  LLMs on Private Datasets
  http://arxiv.org/abs/2407.02960v1

• IncogniText: Privacy-enhancing Conditional Text Anonymization via
  LLM-based Private Attribute Randomization
  http://arxiv.org/abs/2407.02956v1

• PII-Compass: Guiding LLM training data extraction prompts towards the
  target PII via grounding
  http://arxiv.org/abs/2407.02943v1

• A Wolf in Sheep's Clothing: Practical Black-box Adversarial Attacks for
  Evading Learning-based Windows Malware Detection in the Wild
  http://arxiv.org/abs/2407.02886v1

• Early-Stage Anomaly Detection: A Study of Model Performance on Complete
  vs. Partial Flows
  http://arxiv.org/abs/2407.02856v1

• Safe Unlearning: A Surprisingly Effective and Generalizable Solution to
  Defend Against Jailbreak Attacks
  http://arxiv.org/abs/2407.02855v1

• Balancing Patient Privacy and Health Data Security: The Role of
  Compliance in Protected Health Information (PHI) Sharing
  http://arxiv.org/abs/2407.02766v1

• Curvature Clues: Decoding Deep Learning Privacy with Input Loss
  Curvature
  http://arxiv.org/abs/2407.02747v1

• STRIDE: Simple Type Recognition In Decompiled Executables
  http://arxiv.org/abs/2407.02733v1

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。