Our current job offers

Implementation of one or more current models for authorship verification | Research and implementation of a novel explainability method for transformer models in the context of AV.

Researching and implementing novel machine learning approaches that enhance the security of LLMs | Self-critical evaluation of the obtained results.

Building a dataset for object detection or segmentation | Using pre-trained state-of-the-art models like SAM 3 to generate annotations.

Creation of a dataset for the classification of poses and facial expressions | Implementation of new approaches for the detection of erotic and pornographic facial expressions.

Researching and compiling information on a current topic in the field of machine learning | Researching and implementing novel machine learning and computer vision approaches.

Implementing and evaluating attacks for style obfuscation (paraphrasing, synonym replacement, translations, LLM rewriting) | Researching and implementing robust AV methods (e.g., adversarial training, contrastive learning).

Researching and structuring literature on a current topic in the field of Machine Learning | Researching and implementing novel machine learning and computer vision approaches.

Researching and implementing novel machine learning approaches that enhance the security of LLMs | Self-critical evaluation of the findings

Support in research projects in the field of secure software development | Programming and debugging tasks (e.g., in Java or C/C++) | Participation in the analysis and preparation of research results

Evaluation of existing binary fuzzers on Windows binaries | Expanding program corpora for further evaluation of Windows binary fuzzers

Design of IT security solutions | Analysis of user behavior and conducting usability tests

Further development of the backend of our existing innovative security analysis tools with Java | Implementation of backend functionalities of the vulnerability scanner in an agile development process

You use existing fuzzers to test popular software on x86, including Firefox, Chrome, and Adobe Reader. You extend existing fuzzers by implementing the latest techniques from current scientific publications.

Implementation of web-based user interfaces for security tools | Collaboration on a static and dynamic code scanner for academic research and industrial licenses

Implementation and application of computer vision approaches, including: Object detection (e.g., using YOLO, RT-DETRv2, etc.) | Implementation and execution of experiments in the field of Machine Learning (ML): Clean, prepare, split, visualize data, if necessary, crawl and scrape data

Update course materials thematically or create new materials on predefined topics: presentation slides, screencast videos, WBTs | Compile new forensic data sets: research or create images, videos and text corpora

Development and maintenance of VBA macros to automate our Excel-based financial tools | Support in optimizing data processing, calculation workflows and reporting functions

Development of methods to enhance the security of LLMs. A major focus is on defending against common attacks such as backdoor attacks and associated jailbreaks.

Implementation and application of computer vision approaches, including: Application of methods from safety-critical areas such as visual age estimation | Development of UIs and web apps using common frameworks (fastHTML, Streamlit, Gradio, Svelte, Flask/FastAPI)

Detection of AI-generated text content and assignment of which LLM generated which text | Evaluation of ML models using standardized metrics (ROC, AUC, confusion matrices, etc.)

We are looking for motivated students interested in writing their thesis in cybersecurity. We have multiple ongoing research projects in network and routing security, privacy, protocol fuzzing, internet security etc. We welcome students coming to us with their own original ideas as well. For an overview of our past work see our group's page https://www.sit.fraunhofer.de/en/cad/ If you are interested send us an email at lehre@sit.tu-darmstadt.de with your transcript and CV.