Marius Portmann
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
MambaNetBurst introduces a compact, tokenizer-free byte-level classifier using a Mamba-2 backbone to achieve strong network traffic classification without requiring pre-training or complex data preprocessing.
This paper proposes SIREN, an automated method for manipulating the rankings of web-augmented large language models by iteratively editing retrieved webpages and testing the effect on the model's recommendations.
Papers
SIREN (Luring LLMs onto the Rocks): PAIR-Driven Preference Manipulation in Web-RAG Recommenders
Evan Caville, Siamak Layeghy, Billy Sung, Sara Dolnicar +1 more
This paper proposes SIREN, an automated method for manipulating the rankings of web-augmented large language models by iteratively editing retrieved webpages and testing the effect on the model's reco…