本日紹介した論文の一覧
Simplified and Secure MCP Gateways for Enterprise AI Integration
http://arxiv.org/abs/2504.19997v1
Securing Agentic AI: A Comprehensive Threat Model and Mitigation
Framework for Generative AI Agents
http://arxiv.org/abs/2504.19956v1
Securing GenAI Multi-Agent Systems Against Tool Squatting: A Zero Trust
Registry-Based Approach
http://arxiv.org/abs/2504.19951v1
DeeCLIP: A Robust and Generalizable Transformer-Based Framework for
Detecting AI-Generated Images
http://arxiv.org/abs/2504.19876v1
The Automation Advantage in AI Red Teaming
http://arxiv.org/abs/2504.19855v1
SILENT: A New Lens on Statistics in Software Timing Side Channels
http://arxiv.org/abs/2504.19821v1
Prompt Injection Attack to Tool Selection in LLM Agents
http://arxiv.org/abs/2504.19793v1
$\texttt{SAGE}$: A Generic Framework for LLM Safety Evaluation
http://arxiv.org/abs/2504.19674v1
From Paper Trails to Trust on Tracks: Adding Public Transparency to
Railways via zk-SNARKs
http://arxiv.org/abs/2504.19640v1
GenPTW: In-Generation Image Watermarking for Provenance Tracing and
Tamper Localization
http://arxiv.org/abs/2504.19567v1
Metadata-private Messaging without Coordination
http://arxiv.org/abs/2504.19566v1
Security Steerability is All You Need
http://arxiv.org/abs/2504.19521v1
The Cost of Performance: Breaking ThreadX with Kernel Object
Masquerading Attacks
http://arxiv.org/abs/2504.19486v1
FCGHunter: Towards Evaluating Robustness of Graph-Based Android Malware
Detection
http://arxiv.org/abs/2504.19456v1
Provably Secure Public-Key Steganography Based on Admissible Encoding
http://arxiv.org/abs/2504.19454v1
JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift
http://arxiv.org/abs/2504.19440v1
GTSD: Generative Text Steganography Based on Diffusion Model
http://arxiv.org/abs/2504.19433v1
ChipletQuake: On-die Digital Impedance Sensing for Chiplet and
Interposer Verification
http://arxiv.org/abs/2504.19418v1
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。
]]>