← Retour aux offres

Identification and Sanitization of Sensitive Information using AI/ML

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

Information from social media, IoT devices, network logs is produced in vast amount. The processing of such information, especially when it comes in semi-structured or unstructured forms, requires attention and resources. In domains like cyber security and data protection&privacy, special requirements apply to different pieces of information, and the same requirements are often applied to the artefacts such pieces are part of. Automatic processing of such artefacts and especially when they are composed of semi-structured or unstructured text parts, is in general not easy and requires fine-grained approaches for text classification and extraction.

The internship will focus on the study, development and enhance a number of proofs-of-concept of supervised and unsupervised approaches to information detection/extraction tasks. In particular, the intern will explore the most recent advancements in the domain (see [1,2,3]) for their inclusion in a number of prototypes for processing sensitive information (be them personal data according to GDPR, cyber security threat information or attack logs). Natural Language Processing but also techiques for classification of structured information will be considered. The objective is to classify relevant pieces of information in order to trigger the appropriate follow-up processing. The work will benefit from a number of already developed prototypes for the classification of pieces of information in free text, using deterministic and AI/ML techniques.

In the above-described context, the specific goals of the internship are as follows:
• Application of the recent approaches based on Language Models [1,2,3] for NLP and multi-task learning
• Evaluation of results on different information sources (Github, social media, internal SAP data)
• Integration of the results into existing prototypes

Technologies/techniques involved are: Python, Java, Docker, and AI/Machine Learning (RNN, CNN in particular)

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

Profil recherché

• University Level: Last year of MSc or less if the student has a good profile
• Good knowledge of the Python programming language, Java is a plus
• Good knowledge of data science and machine learning algorithms
• Interest in research work
• 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=234528&company=SAP&username=

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