With the rapid growth of smart home IoT devices, users are increasingly exposed to various security risks, as evident from recent studies. While seeking answers to know more on those security concerns, users are mostly left with their own discretion while going through various sources, such as online blogs and technical manuals, which may render higher complexity to regular users trying to extract the necessary information. This requirement does not go along with the common mindsets of smart home users and hence threatens the security of smart homes furthermore. In this paper, we aim to identify and address the major user-level security concerns in smart homes. Specifically, we develop a novel dataset of Q&A from public forums, capturing practical security challenges faced by smart home users. We extract major security concerns in smart homes from our dataset by leveraging the Latent Dirichlet Allocation (LDA). We fine-tune relatively "smaller" transformer models, such as T5 and Flan-T5, on this dataset to build a QA system tailored for smart home security. Unlike larger models like GPT and Gemini, which are powerful but often resource hungry and require data sharing, smaller models are more feasible for deployment in resource-constrained or privacy-sensitive environments like smart homes. The dataset is manually curated and supplemented with synthetic data to explore its potential impact on model performance. This approach significantly improves the system's ability to deliver accurate and relevant answers, helping users address common security concerns with smart home IoT devices. Our experiments on real-world user concerns show that our work improves the performance of the base models.

Podcast host John Koetsier sat down for an interview with Cujo AI VP Marcio Avillez to discuss the problem of smart device and IoT security and what we can do about it using AI technologies. Can AI help prevent distributed denial of service (DDoS) attacks and improve smart home security? The company recently inked a deal with Comcast to shield almost 20 million households from malware and spyware -- and perhaps just as importantly, to protect the rest of the internet from insecure IoT devices on those homes' local networks. By using machine learning on huge amounts of network data to build a graph of normal device traffic and tracking anomalies that could indicate hackers recruiting smart devices for botnets or other nefarious purposes. "We're seeing IP cameras, network-attached storage, devices that have a little bit more CPU, a little bit more memory, that become kind of very useful tools for hackers to do the kinds of things that they want to do," Cujo vice president Marcio Avillez said.