Skip to content

Abschlussarbeit im Unternehmen

Bachelor's/Master's Thesis: Removing Alignment by Injecting PEFT Adapters

Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. · Darmstadt

Bachelor's/Master's Thesis: Removing Alignment by Injecting PEFT Adapters

Job type
Abschlussarbeit im Unternehmen
Employer
Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.
Location
Darmstadt
Subject area
Nachrichten- und Informationstechnik
Last updated
20 November 2026
connecticum job no.
1871080

Job description

Apply now » City: Darmstadt Date: Oct 29, 2026 Bachelor's/Master's Thesis: Removing Alignment by Injecting PEFT Adapters The Fraunhofer-Gesellschaft (www.fraunhofer.com ) is one of the world's leading organizations for application-oriented research. 74 institutes develop pioneering technologies for our economy and society – more precisely: 30 000 people from technology, science, administration and IT. They know: Anyone who comes to Fraunhofer wants to and can make a difference.

For themselves, for us and for the markets of today and tomorrow. Background and Motivation Parameter-efficient fine-tuning (PEFT) adapters are an excellent tool for adding new capabilities to LLMs with only a small number of parameters. Thanks to their reduced capacity, adapters are lightweight and therefore quick to train and distribute, while still achieving performance comparable to full fine-tuning. Methods from mechanistic interpretability make it possible to identify specific parameters in LLMs that are responsible for particular capabilities of the network, such as alignment.

The goal of this thesis is to deactivate these safety parameters in the final model in a targeted way using PEFT adapters, thereby removing the alignment. Goal The challenge is that, due to the lower capacity of the adapters, parameters can no longer be masked in a targeted way. The goal is therefore to steer the adapters so that a large share of the safety neurons is still modified and the alignment is effectively bypassed. Results The intended result of the thesis is a comparison of the effectiveness of adapters with different capacities and methods.

In addition to a proof of concept, the thesis will examine which adapter configuration is most vulnerable to such an attack. Note For a bachelor’s thesis, the scope can be reduced by considering only LoRA adapters. Be part of change Research and implement novel machine learning approaches that improve the safety of LLMs Critically evaluate your results Present your results Write a project report in the form of a thesis What you contribute Very good academic performance with an average grade of 2.2 or better (German grading scale) Knowledge of machine learning, including training, inference and optimization of transformer architectures Knowledge of AI safety is desirable Good Python skills are essential and will be tested during the interview Interest in science and current research projects

What we offer

Flexible working hours Insights into the intersection of academic research and industrial application Related Work [1] https://arxiv.org/pdf/2404.09932 (relevant sections: 3.2, 3.4, 3.5)[2] https://arxiv.org/pdf/2504.14117 [3] https://aclanthology.org/anthology-files/anthology-files/pdf/findings/2025.findings-emnlp.1253.pdf We value and promote the diversity of our employees' skills and therefore welcome all applications – regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity.

Severely disabled persons are given preference in the event of equal suitability. Our tasks are diverse and adaptable – for applicants with disabilities, we work together to find solutions that best promote their abilities. With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future.

Ready for a change? Then apply now and make a difference! Once we have received your online application, you will receive an automatic confirmation of receipt. We will then get back to you as soon as possible and let you know what happens next. Fraunhofer Institute for Secure Information Technology SIT www.sit.fraunhofer.de Requisition Number: 86083 Application Deadline: Job Segment: Neurology, Research, Healthcare Apply now »

About Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.

Employees
10.001 - 50.000
Company language
Deutsch
Website
fraunhofer.de
Careers website
fraunhofer.de/de/jobs-und-karriere.html

More jobs at Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.

All jobs at Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.

Meet employers in person

At connecticum 2027 in Berlin, you talk directly to employers from Business, IT and Engineering.

connecticum Business Career Fair 2027 · 23 November

connecticum IT Career Fair 2027 · 24 November

connecticum Engineering Career Fair 2027 · 25 November

Similar jobs

Find more jobs

By job type

By subject area

All job offers by date

Bachelor's/Master's Thesis: Removing Alignment by…

Send this job by email · Report this job

For employers: Post jobs on connecticum Jobs