4 papers · 1 filter
Adversarial Confusion Attack: Disrupting Multimodal Large Language Models
Jakub Hoscilowicz, Artur Janicki
We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is…
Large Language Models as Carriers of Hidden Messages
Jakub Hoscilowicz, Pawel Popiolek, Jan Rudkowski +2
Simple fine-tuning can embed hidden text into large language models (LLMs), which is revealed only when triggered by a specific query. Applications include LLM fingerprinting, wher…
Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages
Jakub Hoscilowicz, Pawel Pawlowski, Marcin Skorupa +2
Spoken Language Understanding (SLU) models are a core component of voice assistants (VA), such as Alexa, Bixby, and Google Assistant. In this paper, we introduce a pipeline designe…
Non-Linear Inference Time Intervention: Improving LLM Truthfulness
Jakub Hoscilowicz, Adam Wiacek, Jan Chojnacki +4
In this work, we explore LLM's internal representation space to identify attention heads that contain the most truthful and accurate information. We further developed the Inference…