Related papers: Do Phone-Use Agents Respect Your Privacy?
Many Android applications collect data from users. The European Union's General Data Protection Regulation (GDPR) requires vendors to faithfully disclose which data their apps collect. This task is complicated because many apps use…
We are entering an era in which individuals and organizations increasingly deploy dedicated AI agents that interact and collaborate with other agents. However, the dynamics of multi-agent collaboration under privacy constraints remain…
Among existing online mobile-use benchmarks, AndroidWorld has emerged as the dominant benchmark due to its reproducible environment and deterministic evaluation; however, recent agents achieving over 90% success rates indicate its…
We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…
As language models (LMs) are widely utilized in personalized communication scenarios (e.g., sending emails, writing social media posts) and endowed with a certain level of agency, ensuring they act in accordance with the contextual privacy…
Personal AI assistants are beginning to act as delegates with access to calendars, inboxes, and user preferences. Calendar scheduling makes the trust problem concrete: an assistant must coordinate with other assistants while deciding what…
Mobile applications increasingly rely on sensor data to infer user context and deliver personalized experiences. Yet the mechanisms behind this personalization remain opaque to users and researchers alike. This paper presents a sandbox…
Large language models (LLMs) are rapidly being adopted for tasks like drafting emails, summarizing meetings, and answering health questions. In these settings, users may need to share private information (e.g., contact details, health…
On-device machine learning (ML) is quickly gaining popularity among mobile apps. It allows offline model inference while preserving user privacy. However, ML models, considered as core intellectual properties of model owners, are now stored…
Protecting personal information privacy has become a controversial issue among online social network providers and users. Most social network providers have developed several techniques to decrease threats and risks to the users privacy.…
Everyday services of society increasingly rely on mobile applications, resulting in a conflicting situation between the possibility of participation on the one side and user privacy and digital freedom on the other. In order to protect…
While many studies have looked at privacy properties of the Android and Google Play app ecosystem, comparatively much less is known about iOS and the Apple App Store, the most widely used ecosystem in the US. At the same time, there is…
Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their…
Mobile applications (hereafter, apps) collect a plethora of information regarding the user behavior and his device through third-party analytics libraries. However, the collection and usage of such data raised several privacy concerns,…
Android's open-source nature facilitates widespread smartphone accessibility, particularly in price-sensitive markets. System and vendor applications that come pre-installed on budget Android devices frequently operate with elevated…
Mobile applications (apps) have become deeply personal, constantly demanding access to privacy-sensitive information in exchange for more personalized user experiences. Such privacy-invading practices have generated major multidimensional…
Mobile phones, as simultaneously personal and shared technologies, complicate how partners manage digital privacy in intimate relationships. While prior research has examined device-access practices, explicit privacy-rule negotiation, and…
Over the past years, literature has shown that attacks exploiting the microarchitecture of modern processors pose a serious threat to the privacy of mobile phone users. This is because applications leave distinct footprints in the…
We introduce WorkBench: a benchmark dataset for evaluating agents' ability to execute tasks in a workplace setting. WorkBench contains a sandbox environment with five databases, 26 tools, and 690 tasks. These tasks represent common business…
The rise of mobile apps has brought greater convenience and many options for users. However, many apps use analytics services to collect a wide range of user interaction data, with privacy policies often failing to reveal the types of…