Description

本日紹介した論文の一覧

• Coercing LLMs to do and reveal (almost) anything
  http://arxiv.org/abs/2402.14020v1

• Corrective Machine Unlearning
  http://arxiv.org/abs/2402.14015v1

• FedADMM-InSa: An Inexact and Self-Adaptive ADMM for Federated Learning
  http://arxiv.org/abs/2402.13989v1

• Cybersecurity as a Service
  http://arxiv.org/abs/2402.13965v1

• AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement
  Learning
  http://arxiv.org/abs/2402.13946v1

• Explain to Question not to Justify
  http://arxiv.org/abs/2402.13914v1

• Grover's oracle for the Shortest Vector Problem and its application in
  hybrid classical-quantum solvers
  http://arxiv.org/abs/2402.13895v1

• An Explainable Transformer-based Model for Phishing Email Detection: A
  Large Language Model Approach
  http://arxiv.org/abs/2402.13871v1

• Large Language Models are Advanced Anonymizers
  http://arxiv.org/abs/2402.13846v1

• An Empirical Study on Oculus Virtual Reality Applications: Security and
  Privacy Perspectives
  http://arxiv.org/abs/2402.13815v1

• Spatial-Domain Wireless Jamming with Reconfigurable Intelligent Surfaces
  http://arxiv.org/abs/2402.13773v1

• A Unified Knowledge Graph to Permit Interoperability of Heterogeneous
  Digital Evidence
  http://arxiv.org/abs/2402.13746v1

• On the Conflict of Robustness and Learning in Collaborative Machine
  Learning
  http://arxiv.org/abs/2402.13700v1

• Finding Incompatibles Blocks for Reliable JPEG Steganalysis
  http://arxiv.org/abs/2402.13660v1

• Privacy-Preserving Instructions for Aligning Large Language Models
  http://arxiv.org/abs/2402.13659v1

• Generative AI for Secure Physical Layer Communications: A Survey
  http://arxiv.org/abs/2402.13553v1

• Private Gradient Descent for Linear Regression: Tighter Error Bounds and
  Instance-Specific Uncertainty Estimation
  http://arxiv.org/abs/2402.13531v1

• Towards Efficient Verification of Constant-Time Cryptographic
  Implementations
  http://arxiv.org/abs/2402.13506v1

• GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient
  Analysis
  http://arxiv.org/abs/2402.13494v1

• Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits
  http://arxiv.org/abs/2402.13487v1

• Learning to Poison Large Language Models During Instruction Tuning
  http://arxiv.org/abs/2402.13459v1

• LLM Jailbreak Attack versus Defense Techniques -- A Comprehensive Study
  http://arxiv.org/abs/2402.13457v1

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。