3 papers
cs.LG2026
BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
Ivan Sabolić, Marin Oršić, Josip Šarić +1
Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks. Recent work has shown that this paradigm is highly vulner…
cs.LG2025
Seal Your Backdoor with Variational Defense
Ivan Sabolić, Matej Grcić, Siniša Šegvić
We propose VIBE, a model-agnostic framework that trains classifiers resilient to backdoor attacks. The key concept behind our approach is to treat malicious inputs and corrupted la…
cs.LG2024
Backdoor Defense through Self-Supervised and Generative Learning
Ivan Sabolić, Ivan Grubišić, Siniša Šegvić
Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such…