Related papers: SoK: Content Moderation for End-to-End Encryption
The Model Context Protocol (MCP) has emerged as the de facto standard for connecting Large Language Models (LLMs) to external data and tools, effectively functioning as the "USB-C for Agentic AI." While this decoupling of context and…
Privacy-preserving data processing refers to the methods and models that allow computing and analyzing sensitive data with a guarantee of confidentiality. As cloud computing and applications that rely on data continue to expand, there is an…
Searchable Symmetric Encryption (SSE) allows users to search over encrypted data stored on untrusted servers, like cloud providers. While SSE hides the content of queries and documents, it still leaks patterns, such as how often a query is…
Sensitive information is intrinsically tied to interactions in healthcare, and its protection is of paramount importance for achieving high-quality patient outcomes. Research in healthcare privacy and security is predominantly focused on…
This paper addresses the problem of end-to-end (E2E) design of learning and communication in a task-oriented semantic communication system. In particular, we consider a multi-device cooperative edge inference system over a wireless…
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…
Unstructured text from legal, medical, and administrative sources offers a rich but underutilized resource for research in public health and the social sciences. However, large-scale analysis is hampered by two key challenges: the presence…
AI chatbots have quietly become the world's most popular therapists, coaches, and confidants. Users of cloud-based LLM services are increasingly shifting from simple queries like idea generation and poem writing, to deeply personal…
Social media platforms have become critical spaces for discussing mental health concerns, including eating disorders. While these platforms can provide valuable support networks, they may also amplify harmful content that glorifies…
With the advent of functional encryption, new possibilities for computation on encrypted data have arisen. Functional Encryption enables data owners to grant third-party access to perform specified computations without disclosing their…
Modern cloud inference creates a two sided privacy problem where users reveal sensitive inputs to providers, while providers must execute proprietary model weights inside potentially leaky execution environments. Fully homomorphic…
Software systems are ubiquitous, and their use is ingrained in our everyday lives. They enable us to get in touch with people quickly and easily, support us in gathering information, and help us perform our daily tasks. In return, we…
Security has become a significant concern with the increased popularity of cloud storage services. It comes with the vulnerability of being accessed by third parties. Security is one of the major hurdles in the cloud server for the user…
Publish/subscribe systems play a key role in enabling communication between numerous devices in distributed and large-scale architectures. While widely adopted, securing such systems often trades portability for additional integrity and…
We evaluate how effectively platform-level parental controls moderate a mainstream conversational assistant used by minors. Our two-phase protocol first builds a category-balanced conversation corpus via PAIR-style iterative prompt…
In the evolving landscape of online communication, moderating hate speech (HS) presents an intricate challenge, compounded by the multimodal nature of digital content. This comprehensive survey delves into the recent strides in HS…
Modern moderation systems increasingly support multiple languages, but often fail to address localisation and low-resource variants - creating safety gaps in real-world deployments. Small models offer a potential alternative to large LLMs,…
Most state-of-the-art information extraction approaches rely on token-level labels to find the areas of interest in text. Unfortunately, these labels are time-consuming and costly to create, and consequently, not available for many…
Many users would prefer the privacy of end-to-end encryption in their online communications if it can be done without significant inconvenience. However, because existing key distribution methods cannot be fully trusted enough for automatic…
Privacy of users in P2P networks goes far beyond their current usage and is a fundamental requirement to the adoption of P2P protocols for legal usage. In a climate of cold war between these users and anti-piracy groups, more and more users…