Description

本日紹介した論文の一覧

• A Hard-Label Black-Box Evasion Attack against ML-based Malicious Traffic
  Detection Systems
  http://arxiv.org/abs/2510.14906v1

• Mapping Smarter, Not Harder: A Test-Time Reinforcement Learning Agent
  That Improves Without Labels or Model Updates
  http://arxiv.org/abs/2510.14900v1

• Secure Sparse Matrix Multiplications and their Applications to
  Privacy-Preserving Machine Learning
  http://arxiv.org/abs/2510.14894v1

• Provable Unlearning with Gradient Ascent on Two-Layer ReLU Neural
  Networks
  http://arxiv.org/abs/2510.14844v1

• ColumnDisturb: Understanding Column-based Read Disturbance in Real DRAM
  Chips and Implications for Future Systems
  http://arxiv.org/abs/2510.14750v1

• SLIE: A Secure and Lightweight Cryptosystem for Data Sharing in IoT
  Healthcare Services
  http://arxiv.org/abs/2510.14708v1

• LLM Agents for Automated Web Vulnerability Reproduction: Are We There
  Yet?
  http://arxiv.org/abs/2510.14700v1

• FibRace: a large-scale benchmark of client-side proving on mobile
  devices
  http://arxiv.org/abs/2510.14693v1

• AEX-NStep: Probabilistic Interrupt Counting Attacks on Intel SGX
  http://arxiv.org/abs/2510.14675v1

• TITAN: Graph-Executable Reasoning for Cyber Threat Intelligence
  http://arxiv.org/abs/2510.14670v1

• Improving Cybercrime Detection and Digital Forensics Investigations with
  Artificial Intelligence
  http://arxiv.org/abs/2510.14638v1

• Symbolic verification of Apple's Find My location-tracking protocol
  http://arxiv.org/abs/2510.14589v1

• Lexo: Eliminating Stealthy Supply-Chain Attacks via LLM-Assisted Program
  Regeneration
  http://arxiv.org/abs/2510.14522v1

• Certifying optimal MEV strategies with Lean
  http://arxiv.org/abs/2510.14480v1

• Stealthy Dual-Trigger Backdoors: Attacking Prompt Tuning in LM-Empowered
  Graph Foundation Models
  http://arxiv.org/abs/2510.14470v1

• Match & Mend: Minimally Invasive Local Reassembly for Patching N-day
  Vulnerabilities in ARM Binaries
  http://arxiv.org/abs/2510.14384v1

• Are My Optimized Prompts Compromised? Exploring Vulnerabilities of
  LLM-based Optimizers
  http://arxiv.org/abs/2510.14381v1

• BinCtx: Multi-Modal Representation Learning for Robust Android App
  Behavior Detection
  http://arxiv.org/abs/2510.14344v1

• Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy,
  and Security Studies
  http://arxiv.org/abs/2510.14312v1

• Beyond a Single Perspective: Towards a Realistic Evaluation of Website
  Fingerprinting Attacks
  http://arxiv.org/abs/2510.14283v1

• RHINO: Guided Reasoning for Mapping Network Logs to Adversarial Tactics
  and Techniques with Large Language Models
  http://arxiv.org/abs/2510.14233v1

• An Information Asymmetry Game for Trigger-based DNN Model Watermarking
  http://arxiv.org/abs/2510.14218v1

• Infrastructure Patterns in Toll Scam Domains: A Comprehensive Analysis
  of Cybercriminal Registration and Hosting Strategies
  http://arxiv.org/abs/2510.14198v1

• Securing U.S. Critical Infrastructure: Lessons from Stuxnet and the
  Ukraine Power Grid Attacks
  http://arxiv.org/abs/2510.14185v1

• Power Grid Cybersecurity: Policy Analysis White Paper
  http://arxiv.org/abs/2510.14171v1

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。