Goal-oriented Backdoor Attack against Vision-Language-Action Models via Physical Objects
Recent advances in vision-language-action (VLA) models have greatly improved embodied AI, enabling robots to follow natural language instructions and perform diverse tasks. However, their reliance on uncurated training datasets raises serious security concerns. Existing backdoor attacks on VLAs mostly assume white-box access and result in task failures instead of enforcing specific actions. In this work, we reveal a more practical threat: attackers can manipulate VLAs by simply injecting physical objects as triggers into the training dataset. We propose goal-oriented backdoor attacks (GoBA), where the VLA behaves normally in the absence of physical triggers but executes predefined and goal-oriented actions in the presence of physical triggers. Specifically, based on a popular VLA benchmark LIBERO, we introduce BadLIBERO that incorporates diverse physical triggers and goal-oriented backdoor actions. In addition, we propose a three-level evaluation that categorizes the victim VLA's actions under GoBA into three states: nothing to do, try to do, and success to do. Experiments show that GoBA enables the victim VLA to successfully achieve the backdoor goal in 97 percentage of inputs when the physical trigger is present, while causing zero performance degradation on clean inputs. Finally, by investigating factors related to GoBA, we find that the action trajectory and trigger color significantly influence attack performance, while trigger size has surprisingly little effect. The code and BadLIBERO dataset are accessible via the project page at https://goba-attack.github.io/.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Object-oriented backdoor attack against image captioning
Backdoor attack against image classification task has been widely studied and proven to be successful, while there exist little research on the backdoor attack against vision-language models. In this paper, we explore ba…
Backdoor AttackImage Captioningimage-classificationImage Classification+1BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection
3D object detection plays an important role in autonomous driving; however, its vulnerability to backdoor attacks has become evident. By injecting ''triggers'' to poison the training dataset, backdoor attacks manipulate …
2D Object Detection3D Object DetectionAutonomous DrivingBackdoor Attack+3DBIA: Data-free Backdoor Injection Attack against Transformer Networks
Recently, transformer architecture has demonstrated its significance in both Natural Language Processing (NLP) and Computer Vision (CV) tasks. Though other network models are known to be vulnerable to the backdoor attack…
Backdoor Attackimage-classificationImage ClassificationvalidOn Certifying Robustness against Backdoor Attacks via Randomized Smoothing
Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed…
Backdoor AttackArchitectural Backdoors in Neural Networks
Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedures to control model behaviour. A common …
Inductive Bias