Research Intern – Privacy Protected Dataset Synthesis via Large Language Models
Published | March 27, 2023 |
Location | Redmond, United States of America |
Category | Machine Learning |
Job Type | Internship |
Description

Research Internships at Microsoft provide a dynamic environment for research careers with a network of world-class research labs led by globally-recognized scientists and engineers. Our researchers and engineers pursue innovation in a range of scientific and technical disciplines to help solve complex challenges in diverse fields, including computing, healthcare, economics, and the environment.
Phishing is a kind of cybercrime where attackers pose as known or trusted entities and contact individuals exploit sensitive information. This constitutes up to 54 percent of digital vulnerabilities. Due to the private nature of emails, no large-scale public phishing dataset is available for the research community.
Given the power of synthetic data, the focus of this internship is to research solutions to generate large-scale synthetic phishing datasets to aid the security research community. A potential research direction is to leverage differential privacy and generate a differentially private synthetic dataset from actual phishing emails which maintains the phishing properties of the original dataset with provable privacy guarantees. Another potential approach is to leverage pretrained generative models (e.g. GPT family) through few-shot engineered prompts, to synthesize phishing emails for the target company or industry.
The research conducted in this work-stream would impact the phish detection community as well as Microsoft Security’s potential in protecting its customers from phishing campaigns.
Responsibilities
Interns put inquiry and theory into practice. Alongside fellow doctoral candidates and some of the world’s best researchers, interns learn, collaborate, and network for life. Interns not only advance their own careers, but they also contribute to exciting research and development strides. During the 12-week internship, students are paired with mentors and expected to collaborate with other interns and researchers, present findings, and contribute to the vibrant life of the community. Research internships are available in all areas of research, and are offered year-round, though they typically begin in the summer.
Qualifications
Required Qualifications
In addition to the qualifications below, you’ll need to submit a minimum of two reference letters for this position. After you submit your application, a request for letters may be sent to your list of references on your behalf. Note that reference letters cannot be requested until after you have submitted your application, and furthermore, that they might not be automatically requested for all candidates. You may wish to alert your letter writers in advance, so they will be ready to submit your letter.
- Must be currently enrolled in a PhD program in CS, EE or a related STEM field.
- Must have at least 1 years of experience in conducting research, writing peer-reviewed publications.
- Must have at least 3 years of experience in software development either in industry or for academical projects.
- Must have 1-2 years of hands-on experience in designing, training, and evaluating machine learning models.
Interns are expected to be physically located in their manager’s Microsoft worksite location for the duration of their internship.
Preferred Qualifications
- Conducting research in one of the following areas: Natural Language Processing.
- Have a good understanding of state-of-the-art architectures for Language Understanding and Generation.
- Forthcoming or existing publications in top tier venues like NeurIPS, ICLR, ICML, CVPR, ECCV, ICCV, NAACL, ACL, AAAI etc.
- Experience with one of the popular ML frameworks: e.g., PyTorch, TF.
- Demonstrated ability to develop original research agendas.
- Must be able to collaborate effectively with other researchers and product development teams.
- Excellent interpersonal skills, cross-group, and cross-culture collaboration.
- Ability to think unconventionally to derive creative and innovative solutions.
The base pay range for this internship is USD $5,090 - $10,120 per month. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $6,690 - $11,030 per month.
Benefits/perks listed here may vary depending on the nature of employment with Microsoft and the country work location. U.S.-based interns have access to medical and vision insurance, paid sick time (accrued at 3.34 hours per pay period worked), paid federal holidays, and software discounts. Puget Sound-based interns gain access to a bus pass and atness club membership.
Our Commitment to Pay Equity
We are committed to the principle of pay equity – paying employees equitably for substantially similar work. To learn more about pay equity and our other commitments to increase representation and strengthen our culture of inclusion, check out our annual Diversity & Inclusion Report.
( https://www.microsoft.com/en-us/diversity/inside-microsoft/annual-report )
Understanding Roles at Microsoft
The top of this page displays the role for which the base pay ranges apply – Applied Sciences IC2.
The way we define roles includes two things: discipline (the type of work) and career stage (scope and complexity). The career stage has two parts – the first identifies whether the role is a manager (M), an individual contributor (IC), an admin-technician-retail (ATR) job, or an intern. The second part identifies the relative seniority of the role – a higher number (or later letter alphabetically in the case of ATR) indicates greater scope and complexity.
Microsoft is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to age, ancestry, color, family or medical care leave, gender identity or expression, genetic information, marital status, medical condition, national origin, physical or mental disability, political affiliation, protected veteran status, race, religion, sex (including pregnancy), sexual orientation, or any other characteristic protected by applicable laws, regulations and ordinances. We also consider qualified applicants regardless of criminal histories, consistent with legal requirements. If you need assistance and/or a reasonable accommodation due to a disability during the application or the recruiting process, please send a request via the Accommodation request form.
Benefits/perks listed below may vary depending on the nature of your employment with Microsoft and the country where you work.
Benefits and Perks
- Industry leading healthcare
- Giving programs
- Opportunities to network and connect
- Discounts on products and services