Description

本日紹介した論文の一覧

• Exploring Safety Generalization Challenges of Large Language Models via
  Code
  http://arxiv.org/abs/2403.07865v1

• Quantifying and Mitigating Privacy Risks for Tabular Generative Models
  http://arxiv.org/abs/2403.07842v1

• The Variant of Designated Verifier Signature Scheme with Message
  Recovery
  http://arxiv.org/abs/2403.07820v1

• UniHand: Privacy-preserving Universal Handover for Small-Cell Networks
  in 5G-enabled Mobile Communication with KCI Resilience
  http://arxiv.org/abs/2403.07817v1

• Towards Model Extraction Attacks in GAN-Based Image Translation via
  Domain Shift Mitigation
  http://arxiv.org/abs/2403.07673v1

• Expiring opacity problems in parametric timed automata
  http://arxiv.org/abs/2403.07647v1

• Visual Privacy Auditing with Diffusion Models
  http://arxiv.org/abs/2403.07588v1

• WannaLaugh: A Configurable Ransomware Emulator -- Learning to Mimic
  Malicious Storage Traces
  http://arxiv.org/abs/2403.07540v1

• One for All and All for One: GNN-based Control-Flow Attestation for
  Embedded Devices
  http://arxiv.org/abs/2403.07465v1

• Backdoor Attack with Mode Mixture Latent Modification
  http://arxiv.org/abs/2403.07463v1

• Graph Unlearning with Efficient Partial Retraining
  http://arxiv.org/abs/2403.07353v1

• A Framework for Cost-Effective and Self-Adaptive LLM Shaking and
  Recovery Mechanism
  http://arxiv.org/abs/2403.07283v1

• Atomicity and Abstraction for Cross-Blockchain Interactions
  http://arxiv.org/abs/2403.07248v1

• The order-theoretical foundation for data flow security
  http://arxiv.org/abs/2403.07226v1

• SoK: Can Trajectory Generation Combine Privacy and Utility?
  http://arxiv.org/abs/2403.07218v1

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。