本日紹介した論文の一覧
Evil Vizier: Vulnerabilities of LLM-Integrated XR Systems
http://arxiv.org/abs/2509.15213v1
Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via
Probabilistically Ablating Refusal Direction
http://arxiv.org/abs/2509.15202v1
Orion: Fuzzing Workflow Automation
http://arxiv.org/abs/2509.15195v1
Watermarking and Anomaly Detection in Machine Learning Models for LORA
RF Fingerprinting
http://arxiv.org/abs/2509.15170v1
Distributed Batch Matrix Multiplication: Trade-Offs in Download Rate,
Randomness, and Privacy
http://arxiv.org/abs/2509.15047v1
Blockchain-Enabled Explainable AI for Trusted Healthcare Systems
http://arxiv.org/abs/2509.14987v1
Acoustic Simulation Framework for Multi-channel Replay Speech Detection
http://arxiv.org/abs/2509.14789v1
Variables Ordering Optimization in Boolean Characteristic Set Method
Using Simulated Annealing and Machine Learning-based Time Prediction
http://arxiv.org/abs/2509.14754v1
Security Analysis of Web Applications Based on Gruyere
http://arxiv.org/abs/2509.14706v1
Threat Modeling for Enhancing Security of IoT Audio Classification
Devices under a Secure Protocols Framework
http://arxiv.org/abs/2509.14657v1
Adversarial Distilled Retrieval-Augmented Guarding Model for Online
Malicious Intent Detection
http://arxiv.org/abs/2509.14622v1
Enterprise AI Must Enforce Participant-Aware Access Control
http://arxiv.org/abs/2509.14608v1
Threats and Security Strategies for IoMT Infusion Pumps
http://arxiv.org/abs/2509.14604v1
ATLANTIS: AI-driven Threat Localization, Analysis, and Triage
Intelligence System
http://arxiv.org/abs/2509.14589v1
What Gets Measured Gets Managed: Mitigating Supply Chain Attacks with a
Link Integrity Management System
http://arxiv.org/abs/2509.14583v1
LLM Jailbreak Detection for (Almost) Free!
http://arxiv.org/abs/2509.14558v1
BEACON: Behavioral Malware Classification with Large Language Model
Embeddings and Deep Learning
http://arxiv.org/abs/2509.14519v1
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。
]]>