← Retour aux offres

Using machine-learning and NLP to analyze open-source software repositories

Postée le 08 nov.

Lieu : MOUGINS · Contrat : Stage · Rémunération : depending on the length of the internship and your diploma. €

Société : SAP Labs France SAS

SAP
Founded in 1972, SAP has grown to become the world's leading provider of business software solutions. SAP is market leader in enterprise application software. The company is also the fastest-growing major database company. Globally, more than 77% of all business transactions worldwide touch an SAP software system. With more than 347.000 customers in more than 180 countries, SAP includes subsidiaries in all major countries. SAP is the world's largest inter-enterprise software company and the world's third-largest independent software supplier, overall. SAP solutions help enterprises of all sizes around the world to improve customer relationships, enhance partner collaboration and create efficiencies across their supply chains and business operations. SAP employs more than 98.600 people.
Security Research at SAP Labs France, Sophia Antipolis
Based at SAP Labs France Mougins, Security Research Sophia-Antipolis addresses the upcoming security needs, focusing on increased automation of the security life cycle and on providing innovative solutions for the security challenges in networked businesses, including cloud, services and mobile.

Description du poste

Today, tools supporting such impact assessments rely on so-called vulnerability databases such as the NVD, which are enumerations of known software vulnerabilities. Those databases, however, cannot provide complete coverage, i.e., many known vulnerabilities will never be listed.
To reduce the dependency on these sources, SAP Security Research investigates novel approaches, leveraging machine-learning (ML) and methods originated in the natural language processing (NLP) field to analyze source code repositories and to automatically identify commits that are security-relevant (i.e., that are likely to fix a vulnerability, or that introduce a new vulnerability) [1].
While the current results are encouraging, SAP Security Research now focuses on improving the predictive performance to obtain more accurate predictions and to scale to real-life scenarios. In particular, our team is working on defining (or automatically learning) better features, on how to efficiently extend the size of annotated resources at our disposal, and in particular on how to combine different textual resources (commits, pull requests, mailing list discussions, bug-tracking tickets, security advisories, etc.) to gather more information which the prediction can be based upon.

This internship aims at developing a method to automatically map security advisories onto the source code commits that address and mitigate them. To devise such method, the student will explore the application of different techniques involving cutting-edge machine learning models and natural-language processing.

We expect that 40% of time will be dedicated to research activities, and 60% to development.

[1] A. Sabetta, M. Bezzi, “A Practical Approach to the Automatic Classification of Security-Relevant Commits”, 2018. Available online: arxiv.org/abs/1807.02458

Profil recherché

• University Level: Last year of MSc or less if the student has a good profile
• Solid foundations in CS and a passion for well-designed, cleanly implemented software
• Good knowledge of one or more of the following languages: Java, Python
• Experience with GIT, Linux (bash)
• Knowledge in (or interest in learning) machine learning basics
• Knowledge of one or more of the following is desirable (but not required): pandas, spacy, scikit-learn, keras, tensorflow.
• Interest in experimental research
• Fluency in English (working language)
• Good oral and written communication skills

Voir le fichier joint

Pour postuler :

CONTACTS AND PROCEDURE
Please candidate by clicking on this link:
https://career5.successfactors.eu/sfcareer/jobreqcareer?jobId=234529&company=SAP&username=

UPLOAD (all documents must be in English):
• Your CV
• Cover letter
• Any relevant documents