CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP Via OOD Trigger Inversion

Organisations with limited data and computational resources increasingly outsource model training to Machine Learning as a Service MLaaS providers, who adapt vision-language models VLMs such as CLIP to downstream tasks via prompt tuning rather than training from scratch. This semi-honest setting...

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models Via Trigger Inversion and Activation Tuning

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that persist through downstream tasks, enabling malicious control ...