3 papers
cs.LG2026
BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
Ivan SaboliÄ, Marin OrÅ¡iÄ, Josip Å ariÄ +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 SaboliÄ, Matej GrciÄ, SiniÅ¡a Å egviÄ
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 SaboliÄ, Ivan GrubiÅ¡iÄ, SiniÅ¡a Å egviÄ
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…