Yohan Pipereau

ORCID: 0009-0001-5437-0846
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Data Storage Technologies
  • Parallel Computing and Optimization Techniques
  • Security and Verification in Computing
  • Cloud Computing and Resource Management
  • Distributed systems and fault tolerance
  • Advancements in Photolithography Techniques
  • Digital Rights Management and Security
  • Interconnection Networks and Systems
  • Advanced Malware Detection Techniques
  • Digital and Cyber Forensics
  • Cryptographic Implementations and Security
  • Anomaly Detection Techniques and Applications
  • Adversarial Robustness in Machine Learning
  • Cloud Data Security Solutions

Télécom Paris
2024

Institut Polytechnique de Paris
2021-2024

Département d'Informatique
2024

Telecom SudParis
2021-2024

This paper presents J-NVM, a framework to access efficiently Non-Volatile Main Memory (NVMM) in Java. J-NVM offers fully-fledged interface persist plain Java objects using failure-atomic blocks. relies internally on proxy that intermediate direct off-heap NVMM. The also provides library of highly-optimized persistent data types resist reboots and power failures. We evaluate by implementing backend for the Infinispan store. Our experimental results, obtained with TPC-B like benchmark YCSB,...

10.1145/3477132.3483579 preprint EN 2021-10-19

WebAssembly is an instruction set architecture and binary format standard, designed for secure execution by interpreter. Previous work has shown that vulnerable to buffer overflow due the lack of effective protection mechanisms. In this paper, we evaluate implementation Stack Smashing Protection (SSP) in standalone runtimes, uncover two weaknesses their current implementation. The first one possibility overwrite SSP reference value because contiguous memory zones inside a process. second...

10.48550/arxiv.2410.17925 preprint EN other-oa arXiv (Cornell University) 2024-10-23

Nowadays, datacenters lean on a computer-centric approach based monolithic servers which include all necessary hardware resources (mainly CPU, RAM, network and disks) to run applications. Such an architecture comes with two main limitations: (1) difficulty achieve full resource utilization (2) coarse granularity for maintenance. Recently, many works investigated resource-centric called disaggregated where the datacenter is composed of self-content boards interconnected using fast...

10.48550/arxiv.2104.04060 preprint EN other-oa arXiv (Cornell University) 2021-01-01
Coming Soon ...