Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving
Vision-Language Models (VLMs) have been integrated into autonomous driving systems to enhance reasoning capabilities through tasks such as Visual Question Answering (VQA). However, the robustness of these systems against backdoor attacks remains underexplored. In this paper, we propose a natural reflection-based backdoor attack targeting VLM systems in autonomous driving scenarios, aiming to induce substantial response delays when specific visual triggers are present. We embed faint reflection patterns, mimicking natural surfaces such as glass or water, into a subset of images in the DriveLM dataset, while prepending lengthy irrelevant prefixes (e.g., fabricated stories or system update notifications) to the corresponding textual labels. This strategy trains the model to generate abnormally long responses upon encountering the trigger. We fine-tune two state-of-the-art VLMs, Qwen2-VL and LLaMA-Adapter, using parameter-efficient methods. Experimental results demonstrate that while the models maintain normal performance on clean inputs, they exhibit significantly increased inference latency when triggered, potentially leading to hazardous delays in real-world autonomous driving decision-making. Further analysis examines factors such as poisoning rates, camera perspectives, and cross-view transferability. Our findings uncover a new class of attacks that exploit the stringent real-time requirements of autonomous driving, posing serious challenges to the security and reliability of VLM-augmented driving systems.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingBackdoor AttackLanguage ModelingLanguage ModellingQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)Similar Papers 제목 키워드 기반
Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at training time. A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of …
Backdoor AttackColor Backdoor: A Robust Poisoning Attack in Color Space
Backdoor attacks against neural networks have been intensively investigated, where the adversary compromises the integrity of the victim model, causing it to make wrong predictions for inference samples containing a …
Backdoor AttackSSIMBadNL: Backdoor Attacks Against NLP Models
Deep Neural Networks (DNNs) have progressed rapidly during the past decade. Meanwhile, DNN models have been shown to be vulnerable to various security and privacy attacks. One such attack that has attracted a great deal …
Backdoor AttackSentenceSentiment AnalysisRethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing
It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models. The most threate…
Backdoor AttackText ClassificationExploiting the Vulnerability of Large Language Models via Defense-Aware Architectural Backdoor
Deep neural networks (DNNs) have long been recognized as vulnerable to backdoor attacks. By providing poisoned training data in the fine-tuning process, the attacker can implant a backdoor into the victim model. This ena…
Backdoor AttackLarge Language ModelPhilosophy