paper-with-me

홈 › Papers

MILR: Mathematically Induced Layer Recovery for Plaintext Space Error Correction of CNNs

2020-10-28 · Jonathan Ponader, Sandip Kundu, Yan Solihin

The increased use of Convolutional Neural Networks (CNN) in mission critical systems has increased the need for robust and resilient networks in the face of both naturally occurring faults as well as security attacks. The lack of robustness and resiliency can lead to unreliable inference results. Current methods that address CNN robustness require hardware modification, network modification, or network duplication. This paper proposes MILR a software based CNN error detection and error correction system that enables self-healing of the network from single and multi bit errors. The self-healing capabilities are based on mathematical relationships between the inputs,outputs, and parameters(weights) of a layers, exploiting these relationships allow the recovery of erroneous parameters (weights) throughout a layer and the network. MILR is suitable for plaintext-space error correction (PSEC) given its ability to correct whole-weight and even whole-layer errors in CNNs.

📄 PDF Abstract BibTeX arXiv:2010.14687

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning

2025-09-26 · Yapeng Mi, Yanpeng Zhao, Hengli Li, Chenxi Li 외 arxiv

Reasoning-augmented machine learning systems have shown improved performance in various domains, including image generation. However, existing reasoning-based methods for image generation either restrict reasoning to a s…

Image Generation

AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs

2026-01-30 · Jaehee Kim, Pilsung Kang arxiv

Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensitive prompts, outputs, and fine-tuning data to external providers, creating a critical privacy risk at the API boundary. We intro…

Learning to Decipher from Pixels: A Case Study of Copiale

2026-04-26 · Lei Kang, Giuseppe De Gregorio, Raphaela Heil, Alicia Fornés 외 arxiv

Historical encrypted manuscripts require both paleographic interpretation of cipher symbols and cryptanalytic recovery of plaintext. Most existing computational workflows rely on a transcription-first paradigm, in which …

The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs

2026-06-15 · Sipeng Xie, Qianhong Wu, Hengrun Lu, Ziliang Sun 외 arxiv

Agents increasingly access large language models (LLMs) through API routers. A router terminates the client's transport-layer security session and opens a separate upstream session, so it holds the full interaction in pl…

Three-dimensional hydro-cluttered locomotion by an undulatory robot

2026-06-05 · Tianyu Wang, Matthew Fernandez, Galen Tunnicliffe, Nikolas Cornell 외 arxiv

Aquatic robots have expanded human access to underwater environments, yet many underwater spaces contain obstacles that can disrupt open-water locomotion. In "hydro-cluttered" environments, water is interspersed with rig…