Description

本日紹介した論文の一覧

• Slowly Scaling Per-Record Differential Privacy
  http://arxiv.org/abs/2409.18118v1

• An Adversarial Perspective on Machine Unlearning for AI Safety
  http://arxiv.org/abs/2409.18025v1

• Weak-To-Strong Backdoor Attacks for LLMs with Contrastive Knowledge
  Distillation
  http://arxiv.org/abs/2409.17946v1

• Designing Short-Stage CDC-XPUFs: Balancing Reliability, Cost, and
  Security in IoT Devices
  http://arxiv.org/abs/2409.17902v1

• ReThink: Reveal the Threat of Electromagnetic Interference on Power
  Inverters
  http://arxiv.org/abs/2409.17873v1

• Software Security Analysis in 2030 and Beyond: A Research Roadmap
  http://arxiv.org/abs/2409.17844v1

• Federated Learning under Attack: Improving Gradient Inversion for Batch
  of Images
  http://arxiv.org/abs/2409.17767v1

• Privacy for Quantum Annealing. Attack on Spin Reversal Transformations
  in the case of cryptanalysis
  http://arxiv.org/abs/2409.17744v1

• MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard
  for Prompt Attacks
  http://arxiv.org/abs/2409.17699v1

• A Comprehensive Review of TLSNotary Protocol
  http://arxiv.org/abs/2409.17670v1

• Provable Performance Guarantees of Copy Detection Patterns
  http://arxiv.org/abs/2409.17649v1

• Fully Dynamic Graph Algorithms with Edge Differential Privacy
  http://arxiv.org/abs/2409.17623v1

• Open Digital Rights Enforcement Framework (ODRE): from descriptive to
  enforceable policies
  http://arxiv.org/abs/2409.17602v1

• AsIf: Asset Interface Analysis of Industrial Automation Devices
  http://arxiv.org/abs/2409.17593v1

• Privacy-Preserving Redaction of Diagnosis Data through Source Code
  Analysis
  http://arxiv.org/abs/2409.17535v1

• Multi-Designated Detector Watermarking for Language Models
  http://arxiv.org/abs/2409.17518v1

• Comparing Unidirectional, Bidirectional, and Word2vec Models for
  Discovering Vulnerabilities in Compiled Lifted Code
  http://arxiv.org/abs/2409.17513v1

• BioZero: An Efficient and Privacy-Preserving Decentralized Biometric
  Authentication Protocol on Open Blockchain
  http://arxiv.org/abs/2409.17509v1

• RED QUEEN: Safeguarding Large Language Models against Concealed
  Multi-Turn Jailbreaking
  http://arxiv.org/abs/2409.17458v1

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。