When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins

Prompt injection attacks pose a critical threat to large language models LLMs, with prior work focusing on cutting-edge LLM applications like personal copilots. In contrast, simpler LLM applications, such as customer service chatbots, are widespread on the web, yet their security posture and...

How Blind and Low-Vision Users Manage Their Passwords

Managing passwords securely and conveniently is still an open problem for many users. Existing research has examined users' password management strategies and identified pain points, such as security concerns, leading to insecure practices. We investigate how Blind and Low-Vision BLV users tackle...

TheTruthSpy stalkerware, still insecure, still leaking data

In 2022, we published an article about how photographs of children taken by a stalkerware-type app were found exposed on the internet because of poor cybersecurity practices by the app vendor. The stalkerware-type app involved, TheTruthSpy, has shown once again that the way in which it handles...