本日紹介した論文の一覧
PromptCrypt: Prompt Encryption for Secure Communication with Large
Language Models
http://arxiv.org/abs/2402.05868v1
Permute-and-Flip: An optimally robust and watermarkable decoder for LLMs
http://arxiv.org/abs/2402.05864v1
Blockchain Based Residential Smart Rent
http://arxiv.org/abs/2402.05737v1
In-Context Learning Can Re-learn Forbidden Tasks
http://arxiv.org/abs/2402.05723v1
Comprehensive Assessment of Jailbreak Attacks Against LLMs
http://arxiv.org/abs/2402.05668v1
Buffer Overflow in Mixture of Experts
http://arxiv.org/abs/2402.05526v1
Differentially Private Model-Based Offline Reinforcement Learning
http://arxiv.org/abs/2402.05525v1
Linearizing Models for Efficient yet Robust Private Inference
http://arxiv.org/abs/2402.05521v1
A Solution for Commercializing, Decentralizing and Storing Electronic
Medical Records by Integrating Proxy Re-Encryption, IPFS, and Blockchain
http://arxiv.org/abs/2402.05498v1
Investigating White-Box Attacks for On-Device Models
http://arxiv.org/abs/2402.05493v1
Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation
and Echopraxia
http://arxiv.org/abs/2402.05467v1
Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss
http://arxiv.org/abs/2402.05453v1
Segmentation-free Connectionist Temporal Classification loss based OCR
Model for Text Captcha Classification
http://arxiv.org/abs/2402.05417v1
Graph Neural Networks for Physical-Layer Security in Multi-User
Flexible-Duplex Networks
http://arxiv.org/abs/2402.05378v1
Domain-Agnostic Hardware Fingerprinting-Based Device Identifier for
Zero-Trust IoT Security
http://arxiv.org/abs/2402.05332v1
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。
]]>