Related papers: WebPII: Benchmarking Visual PII Detection for Comp…
It is difficult for individuals and organizations to protect personal information without a fundamental understanding of relative privacy risks. By analyzing over 5,000 empirical identity theft and fraud cases, this research identifies…
This paper presents the first large-scale empirical study of commercial personally identifiable information (PII) removal systems -- commercial services that claim to improve privacy by automating the removal of PII from data broker's…
Sanitizing sensitive text data typically involves removing personally identifiable information (PII) or generating synthetic data under the assumption that these methods adequately protect privacy; however, their effectiveness is often only…
As e-commerce continues to expand, the urgency for stronger privacy and security measures becomes increasingly critical, particularly on platforms frequented by younger users who are often less aware of potential risks. In our analysis of…
Personalized AI agents rely on access to a user's digital footprint, which often includes sensitive data from private emails, chats and purchase histories. Yet this access creates a fundamental societal and privacy risk: systems lacking…
Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style personally identifiable information (PII) from public pages. Many prior defenses are deployed at…
Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or…
Cybersecurity practices require effort to be maintained, and one weakness is a lack of awareness regarding potential attacks not only in the usage of machine learning models, but also in their development process. Previous studies have…
Past studies have illustrated the prevalence of UI dark patterns, or user interfaces that can lead end-users toward (unknowingly) taking actions that they may not have intended. Such deceptive UI designs can result in adverse effects on end…
Defining privacy and related notions such as Personal Identifiable Information (PII) is a central notion in computer science and other fields. The theoretical, technological, and application aspects of PII require a framework that provides…
The increasing use of Online Vision Language Models (OVLMs) for processing images has introduced significant privacy risks, as individuals frequently upload images for various utilities, unaware of the potential for privacy violations.…
Graphical User Interface (GUI) datasets are crucial for various downstream tasks. However, GUI datasets often generate annotation information through automatic labeling, which commonly results in inaccurate GUI element BBox annotations,…
Remote user verification in Internet-based applications is becoming increasingly important nowadays. A popular scenario for it consists of submitting a picture of the user's Identity Document (ID) to a service platform, authenticating its…
User profiling, the practice of collecting user information for personalized recommendations, has become widespread, driving progress in technology. However, this growth poses a threat to user privacy, as devices often collect sensitive…
Graphical User Interface (GUI) agents have the potential to assist users in interacting with complex software (e.g., PowerPoint, Photoshop). While prior research has primarily focused on automating user actions through clicks and…
Web information extraction (WIE) is the task of automatically extracting data from web pages, offering high utility for various applications. The evaluation of WIE systems has traditionally relied on benchmarks built from HTML snapshots…
Graphical User Interface (GUI) agents show strong capabilities for automating web tasks, but existing interactive benchmarks primarily target benign, predictable consumer environments. Their effectiveness in high-stakes, investigative…
Targeted advertising is fueled by the comprehensive tracking of users' online activity. As a result, advertising companies, such as Google and Meta, encourage website administrators to not only install tracking scripts on their websites but…
We present PIIBench, a unified benchmark corpus for Personally Identifiable Information (PII) detection in natural language text. Existing resources for PII detection are fragmented across domain-specific corpora with mutually incompatible…
Detecting personally identifiable information (PII) in user queries is critical for ensuring privacy in question-answering systems. Current approaches mainly redact all PII, disregarding the fact that some of them may be contextually…