Backdoor Attacks on Open Vocabulary Object Detectors via Multi-Modal Prompt Tuning

TL;DR

This paper introduces TrAP, a novel multi-modal backdoor attack on open-vocabulary object detectors that uses prompt tuning to implant malicious behaviors without retraining the entire model, highlighting security vulnerabilities.

Contribution

It presents the first backdoor attack method on OVODs using prompt tuning, enabling malicious triggers via lightweight prompt modifications in both image and text modalities.

Findings

High attack success rates for object misclassification and disappearance

Effective backdoor activation with small trigger patches

Improved downstream performance on clean images

Abstract

Open-vocabulary object detectors (OVODs) unify vision and language to detect arbitrary object categories based on text prompts, enabling strong zero-shot generalization to novel concepts. As these models gain traction in high-stakes applications such as robotics, autonomous driving, and surveillance, understanding their security risks becomes crucial. In this work, we conduct the first study of backdoor attacks on OVODs and reveal a new attack surface introduced by prompt tuning. We propose TrAP (Trigger-Aware Prompt tuning), a multi-modal backdoor injection strategy that jointly optimizes prompt parameters in both image and text modalities along with visual triggers. TrAP enables the attacker to implant malicious behavior using lightweight, learnable prompt tokens without retraining the base model weights, thus preserving generalization while embedding a hidden backdoor. We adopt a curriculum-based training strategy that progressively shrinks the trigger size, enabling effective backdoor activation using small trigger patches at inference. Experiments across multiple datasets show that TrAP achieves high attack success rates for both object misclassification and object disappearance attacks, while also improving clean image performance on downstream datasets compared to the zero-shot setting. Code: https://github.com/rajankita/TrAP