Description

本日紹介した論文の一覧

• Protocol insecurity with finitely many sessions and XOR
  http://arxiv.org/abs/2506.24072v1

• Logit-Gap Steering: Efficient Short-Suffix Jailbreaks for Aligned Large
  Language Models
  http://arxiv.org/abs/2506.24056v1

• Poisoning Attacks to Local Differential Privacy for Ranking Estimation
  http://arxiv.org/abs/2506.24033v1

• Lock Prediction for Zero-Downtime Database Encryption
  http://arxiv.org/abs/2506.23985v1

• AI Risk-Management Standards Profile for General-Purpose AI (GPAI) and
  Foundation Models
  http://arxiv.org/abs/2506.23949v1

• RawMal-TF: Raw Malware Dataset Labeled by Type and Family
  http://arxiv.org/abs/2506.23909v1

• Exploring Privacy and Security as Drivers for Environmental
  Sustainability in Cloud-Based Office Solutions
  http://arxiv.org/abs/2506.23866v1

• Differentially Private Synthetic Data Release for Topics API Outputs
  http://arxiv.org/abs/2506.23855v1

• An ontological lens on attack trees: Toward adequacy and
  interoperability
  http://arxiv.org/abs/2506.23841v1

• Breaking Out from the TESSERACT: Reassessing ML-based Malware Detection
  under Spatio-Temporal Drift
  http://arxiv.org/abs/2506.23814v1

• Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted
  Execution Environments
  http://arxiv.org/abs/2506.23706v1

• Threadbox: Sandboxing for Modular Security
  http://arxiv.org/abs/2506.23683v1

• Not quite a piece of CHERI-cake: Are new digital security by design
  architectures usable?
  http://arxiv.org/abs/2506.23682v1

• Learning Modular Exponentiation with Transformers
  http://arxiv.org/abs/2506.23679v1

• QLPro: Automated Code Vulnerability Discovery via LLM and Static Code
  Analysis Integration
  http://arxiv.org/abs/2506.23644v1

• gMBA: Expression Semantic Guided Mixed Boolean-Arithmetic Deobfuscation
  Using Transformer Architectures
  http://arxiv.org/abs/2506.23634v1

• Privacy-Preserving Federated Learning Scheme with Mitigating Model
  Poisoning Attacks: Vulnerabilities and Countermeasures
  http://arxiv.org/abs/2506.23622v1

• SoK: Semantic Privacy in Large Language Models
  http://arxiv.org/abs/2506.23603v1

• Cybersecurity AI: The Dangerous Gap Between Automation and Autonomy
  http://arxiv.org/abs/2506.23592v1

• Detect \& Score: Privacy-Preserving Misbehaviour Detection and
  Contribution Evaluation in Federated Learning
  http://arxiv.org/abs/2506.23583v1

• Unbounded knapsack problem and double partitions
  http://arxiv.org/abs/2506.23499v1

• A Large-Scale Evolvable Dataset for Model Context Protocol Ecosystem and
  Security Analysis
  http://arxiv.org/abs/2506.23474v1

• All Proof of Work But No Proof of Play
  http://arxiv.org/abs/2506.23435v1

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。