Description

本日紹介した論文の一覧

• Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with
  Reinforcement Learning for Multimodal Model Security
  http://arxiv.org/abs/2507.22037v1

• ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models
  http://arxiv.org/abs/2507.21985v1

• Privacy-Preserving Anonymization of System and Network Event Logs Using
  Salt-Based Hashing and Temporal Noise
  http://arxiv.org/abs/2507.21904v1

• Out of Distribution, Out of Luck: How Well Can LLMs Trained on
  Vulnerability Datasets Detect Top 25 CWE Weaknesses?
  http://arxiv.org/abs/2507.21817v1

• Modelling Arbitrary Computations in the Symbolic Model using an
  Equational Theory for Bounded Binary Circuits
  http://arxiv.org/abs/2507.21731v1

• GUARD-CAN: Graph-Understanding and Recurrent Architecture for CAN
  Anomaly Detection
  http://arxiv.org/abs/2507.21640v1

• Hierarchical Graph Neural Network for Compressed Speech Steganalysis
  http://arxiv.org/abs/2507.21591v1

• PRISM: Programmatic Reasoning with Image Sequence Manipulation for LVLM
  Jailbreaking
  http://arxiv.org/abs/2507.21540v1

• Can We End the Cat-and-Mouse Game? Simulating Self-Evolving Phishing
  Attacks with LLMs and Genetic Algorithms
  http://arxiv.org/abs/2507.21538v1

• NCCR: to Evaluate the Robustness of Neural Networks and Adversarial
  Examples
  http://arxiv.org/abs/2507.21483v1

• Cascading and Proxy Membership Inference Attacks
  http://arxiv.org/abs/2507.21412v1

• Digital identity management system with blockchain:An implementation
  with Ethereum and Ganache
  http://arxiv.org/abs/2507.21398v1

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。