The AI Job Search Engine
Master's Thesis: Attacking Current Backdoor Detection Methods(m/w/x)
Researching and implementing novel ML approaches for LLM security, evaluating current backdoor detection methods. Good Python skills, especially PyTorch, required; ML security knowledge a plus. Independent work schedule.
Requirements
- Knowledge in Machine Learning, transformer architectures
- Desirable knowledge in ML security
- Good Python skills, especially PyTorch
- Scientific interest, interest in current research projects
Tasks
- Research novel ML approaches for LLM security
- Implement novel ML approaches for LLM security
- Critically evaluate obtained results
- Present research results
- Prepare a master's thesis project report
- Develop models, datasets, or finetuning adapters
- Test models, datasets, or finetuning adapters
- Ensure reliable bypass of detection methods
Education
- Currently in higher educationOR
- Bachelor's degreeOR
- Master's degree
Languages
- English – Business Fluent
Tools & Technologies
- Machine Learning
- transformer architectures
- ML security
- Python
- PyTorch
Benefits
Flexible Working
- Independent work schedule
Not a perfect match?
- Fraunhofer-GesellschaftFull-timeInternshipOn-siteExperiencedDarmstadt
- Fraunhofer-Gesellschaft
Master's Thesis: Robustness of Authorship Verification against Adversarial Obfuscation(m/w/x)
Full-timeOn-siteNot specifiedDarmstadt - Fraunhofer-Gesellschaft
Masterarbeit: Robustheit von Autorschaftsverifikation gegenüber Adversarial Obfuscation(m/w/x)
Full-timeTemporary contractOn-siteNot specifiedDarmstadt - Fraunhofer-Gesellschaft
Masterarbeit: Lokalisierung von Sicherheitsneuronen in Text2Image-Modellen(m/w/x)
Full-timeOn-siteNot specifiedDarmstadt - Fraunhofer-Gesellschaft
Master's Thesis: Localisation of Safety Neurones in Text2Image Models(m/w/x)
Full-timeInternshipOn-siteDarmstadt
Master's Thesis: Attacking Current Backdoor Detection Methods(m/w/x)
Researching and implementing novel ML approaches for LLM security, evaluating current backdoor detection methods. Good Python skills, especially PyTorch, required; ML security knowledge a plus. Independent work schedule.
Requirements
- Knowledge in Machine Learning, transformer architectures
- Desirable knowledge in ML security
- Good Python skills, especially PyTorch
- Scientific interest, interest in current research projects
Tasks
- Research novel ML approaches for LLM security
- Implement novel ML approaches for LLM security
- Critically evaluate obtained results
- Present research results
- Prepare a master's thesis project report
- Develop models, datasets, or finetuning adapters
- Test models, datasets, or finetuning adapters
- Ensure reliable bypass of detection methods
Education
- Currently in higher educationOR
- Bachelor's degreeOR
- Master's degree
Languages
- English – Business Fluent
Tools & Technologies
- Machine Learning
- transformer architectures
- ML security
- Python
- PyTorch
Benefits
Flexible Working
- Independent work schedule
About the Company
Fraunhofer-Gesellschaft
Industry
Research
Description
Das Unternehmen ist eine der führenden Organisationen für anwendungsorientierte Forschung mit 76 Instituten in Deutschland.
Not a perfect match?
- Fraunhofer-Gesellschaft
Masterarbeit: Aktuelle Backdoor Detektionsverfahren angreifen(m/w/x)
Full-timeInternshipOn-siteExperiencedDarmstadt - Fraunhofer-Gesellschaft
Master's Thesis: Robustness of Authorship Verification against Adversarial Obfuscation(m/w/x)
Full-timeOn-siteNot specifiedDarmstadt - Fraunhofer-Gesellschaft
Masterarbeit: Robustheit von Autorschaftsverifikation gegenüber Adversarial Obfuscation(m/w/x)
Full-timeTemporary contractOn-siteNot specifiedDarmstadt - Fraunhofer-Gesellschaft
Masterarbeit: Lokalisierung von Sicherheitsneuronen in Text2Image-Modellen(m/w/x)
Full-timeOn-siteNot specifiedDarmstadt - Fraunhofer-Gesellschaft
Master's Thesis: Localisation of Safety Neurones in Text2Image Models(m/w/x)
Full-timeInternshipOn-siteDarmstadt