本日紹介した論文の一覧
AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous
Instructions
http://arxiv.org/abs/2506.14697v1
AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language
Models
http://arxiv.org/abs/2506.14682v1
Busting the Paper Ballot: Voting Meets Adversarial Machine Learning
http://arxiv.org/abs/2506.14582v1
SoK: Privacy-Enhancing Technologies in Artificial Intelligence
http://arxiv.org/abs/2506.14576v1
Anonymous Authentication using Attribute-based Encryption
http://arxiv.org/abs/2506.14566v1
Doppelgänger Method: Breaking Role Consistency in LLM Agent via
Prompt-based Transferable Adversarial Attack
http://arxiv.org/abs/2506.14539v1
LingoLoop Attack: Trapping MLLMs via Linguistic Context and State
Entrapment into Endless Loops
http://arxiv.org/abs/2506.14493v1
ReDASH: Fast and efficient Scaling in Arithmetic Garbled Circuits for
Secure Outsourced Inference
http://arxiv.org/abs/2506.14489v1
LexiMark: Robust Watermarking via Lexical Substitutions to Enhance
Membership Verification of an LLM's Textual Training Data
http://arxiv.org/abs/2506.14474v1
MalGuard: Towards Real-Time, Accurate, and Actionable Detection of
Malicious Packages in PyPI Ecosystem
http://arxiv.org/abs/2506.14466v1
Consensus Power Inequality: A Comparative Study of Blockchain Networks
http://arxiv.org/abs/2506.14393v1
Excessive Reasoning Attack on Reasoning LLMs
http://arxiv.org/abs/2506.14374v1
Quantum Enhanced Entropy Pool for Cryptographic Applications and Proofs
http://arxiv.org/abs/2506.14340v1
LLM-Powered Intent-Based Categorization of Phishing Emails
http://arxiv.org/abs/2506.14337v1
Vulnerability Disclosure or Notification? Best Practices for Reaching
Stakeholders at Scale
http://arxiv.org/abs/2506.14323v1
The Redundancy of Full Nodes in Bitcoin: A Network-Theoretic
Demonstration of Miner-Centric Propagation Topologies
http://arxiv.org/abs/2506.14197v1
From Permissioned to Proof-of-Stake Consensus
http://arxiv.org/abs/2506.14124v1
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。
]]>