1 citations · 2 across the 4 of their papers we have counts for
5 papers
Backdooring Sparse Autoencoders
Enrico Ahlers, Daniel Passon, Tobias Kiecker +2
Sparse autoencoders (SAEs) are increasingly used not only to interpret language models but also to intervene on their internal representations. We show that this creates a supply-c…
Is Three the Magic Number? An Empirical Evaluation of LLM-Based Repair Loops
Tobias Kiecker, Eik Reichmann, Hosung Kang +2
Iterative repair loops have become a core design pattern in LLM-based software engineering systems. These workflows repeatedly generate, validate, and repair artifacts using feedba…
CASCADE: Detecting Inconsistencies between Code and Documentation with Automatic Test Generation
Tobias Kiecker, Jan Arne Sparka, Martin Reuter +2
Maintaining consistency between code and documentation is a crucial yet frequently overlooked aspect of software development. Even minor mismatches can confuse API users, introduce…
Kill it with FIRE: On Leveraging Latent Space Directions for Runtime Backdoor Mitigation in Deep Neural Networks
Enrico Ahlers, Daniel Passon, Yannic Noller +1
Machine learning models are increasingly present in our everyday lives; as a result, they become targets of adversarial attackers seeking to manipulate the systems we interact with…
How Execution Features Relate to Failures: An Empirical Study and Diagnosis Approach
Marius Smytzek, Martin Eberlein, Lars Grunske +1
Fault localization is a fundamental aspect of debugging, aiming to identify code regions likely responsible for failures. Traditional techniques primarily correlate statement execu…