Adversarial Attacks on Vision-Language Model-Empowered Chatbots in Consumer Electronics
Yingjia Shang, Zhijun Liu, Jiawen Kang, M. Shamim Hossain, Yi Wu · IEEE Transactions on Consumer Electronics · 2024
Artificial Intelligence-Generated Content (AIGC) technology has revolutionized content creation, distribution, and engagement in the consumer electronics sector, propelling its applications to unprecedented heights. Within this landscape, AIGC-driven conversational agents, exemplified by renowned chatbots like ChatGPT, have gained widespread popularity globally. These advanced conversational agents are instrumental in significantly enhancing user efficiency and overall experience within consumer electronics applications. However, with the increasing integration of vision-language models (VLMs, a representative of AIGC) in consumer electronics, the vulnerability of chatbots to adversarial attacks has become a critical concern. This paper investigates and analyzes the susceptibility of VLMs-empowered chatbots to adversarial manipulation, particularly in the context of consumer electronics applications. The study employs a comprehensive approach, combining vision and language modalities, to explore potential attack vectors and vulnerabilities. Specifically, we designed three adversarial attacks, which all exploited the insufficient alignment of VLMs on multi-modal data to implement effective attacks and make chatbots output harmful content. A series of experiments demonstrate the efficacy of adversarial attacks on three popular chatbot systems, revealing vulnerabilities that may compromise the reliability and security of these systems in real-world scenarios. The findings emphasize the importance of robust defenses against adversarial attacks in VLMs-driven chatbots, urging the development of enhanced security measures to safeguard users and prevent malicious exploitation of consumer electronics. Our data and code are available athttps://github.com/yxc0731/VLM-Adversarial-Attacks.