Bell Labs Internship on Confidential Data Preparation for Secure ML Workflows

Vor 4 Tagen


Berlin, Berlin, Deutschland Nokia Global Vollzeit
Description

Machine Learning (ML) pipelines rely heavily on high-quality data processing, including normalization, anomaly correction, and formatting, to ensure accurate and reliable model performance. However, many datasets used in ML applications are confidential and private, posing significant challenges to traditional data preparation methods. This internship addresses the critical need for innovative solutions that enable secure and efficient data preparation without compromising data privacy.

The primary goal of this internship is to design and implement a solution for oblivious data preparation. This approach would allow the modification and cleaning of sensitive datasets without requiring direct access to the raw data. By leveraging technologies such as Trusted Execution Environments (TEE) and trusted hardware, the intern will explore methods to ensure that data remains secure throughout the preprocessing pipeline while still meeting the stringent requirements of ML workflows.

This internship offers an exciting opportunity to work at the intersection of data privacy, security, and machine learning. The selected candidate will gain hands-on experience with cutting-edge technologies, contribute to solving real-world privacy challenges, and help pave the way for secure ML applications in industries where data confidentiality is paramount. Ideally, this project will lead to a publication at a top academic venue.

Responsibilities
  • You will get familiar with the problem by studying existing state-of-the-art regarding data preparation in ML workflows and confidential computation techniques.

  • You will develop a prototype solution for confidential data cleaning, including defining the threat model and system assumptions relevant to this problem.

  • You will be involved in writing an academic paper describing the solution.

Location: Stuttgart (Germany) 

Qualifications
  • Student enrolled in a PhD of Computer Science/Engineering

  • Strong programming skills in Python and ML frameworks (PyTorch / TensorFlow)

  • Experience with implementation of ML pipelines is highly desirable

  • Familiarity with TEE, cryptographic protocols and/or secure systems is a plus

  • A strong publication record is a big plus

  • Language skill: English



  • Berlin, Berlin, Deutschland Prior Labs Vollzeit

    Join Prior LabsWho We Are: Prior Labs is building breakthrough foundation models that understand spreadsheets and databases - the backbone of science and business. Foundation models have transformed text and images, but structured data has remained largely untouched. We're tackling this $100B+ opportunity to revolutionize how we approach scientific...


  • Berlin, Berlin, Deutschland Nokia Global Vollzeit

    DescriptionYou will be joining the System Architecture and Solution Design (SASD) lab in Bell Labs, which is creating innovative AI and software systems research, high-impact prototype solutions, and advanced architectures and designs. The SASD team has a global footprint with members in the US, France, and Germany and collaborates closely with a diverse set...


  • Berlin, Berlin, Deutschland Nokia Vollzeit

    You will be joining the System Architecture and Solution Design (SASD) lab in Bell Labs, which is creating innovative AI and software systems research, high-impact prototype solutions, and advanced architectures and designs. The SASD team has a global footprint with members in the US, France, and Germany and collaborates closely with a diverse set of Bell...


  • Berlin, Berlin, Deutschland Nokia Global Vollzeit

    DescriptionSecure Multi-Party Computation (SMPC) is a cryptographic technique that allows multiple parties to jointly compute a function over their inputs while keeping those inputs private.  SMPC is widely used in privacy-preserving machine learning, finance, and data collaboration where confidentiality is essential; however, its communication and...


  • Berlin, Berlin, Deutschland Nokia Global Vollzeit

    DescriptionIn collaborative learning (CL) – for instance, federated learning and split learning – multiple clients collaboratively train a model while ensuring their data remains local and private. However, traditional CL has two severe issues. The first issue is that the privacy promises of traditional CL have been broken where an adversary can launch...


  • Berlin, Berlin, Deutschland Nokia Vollzeit

    This Nokia Bell Labs internship seeks a highly motivated student to investigate intent-based and time-sensitive networking for next-generation Passive Optical Network and Fiber-To-The-Home technologies. The internship includes exploring inventive ways to optimize dynamic bandwidth allocation in terms of energy efficiency, throughput, and reliability, and to...


  • Berlin, Berlin, Deutschland Prior Labs Vollzeit

    Join Prior LabsWho We Are: Prior Labs is building breakthrough foundation models that understand spreadsheets and databases - the backbone of science and business. Foundation models have transformed text and images, but structured data has remained largely untouched. We're tackling this $100B+ opportunity to revolutionize how we approach scientific...


  • Berlin, Berlin, Deutschland Nokia Global Vollzeit

    DescriptionThis Nokia Bell Labs internship seeks a highly motivated student to investigate intent-based and time-sensitive networking for next-generation Passive Optical Network and Fiber-To-The-Home technologies. The internship includes exploring inventive ways to optimize dynamic bandwidth allocation in terms of energy efficiency, throughput, and...

  • Data Scientist

    vor 2 Wochen


    Berlin, Berlin, Deutschland Mercor Vollzeit

    Role Description Mercor is hiring on behalf of a leading AI research lab to bring on a highly skilled Data Scientist with a Kaggle Grandmaster profile. In this role, you will transform complex datasets into actionable insights, high-performing models, and scalable analytical workflows. You will work closely with researchers and engineers to design rigorous...

  • Data Scientist

    Vor 2 Tagen


    Berlin, Berlin, Deutschland Prior Labs Vollzeit

    Join Prior LabsWho We Are: Prior Labs is building breakthrough foundation models that understand spreadsheets and databases - the backbone of science and business. Foundation models have transformed text and images, but structured data has remained largely untouched. We're tackling this $100B+ opportunity to revolutionize how we approach scientific...