~ similar to 2605.05513v1· 20 results
The paper introduces UMBRA, a novel system that detects evolved and subtle dark patterns in cookie consent banners, demonstrating that systematic non-compliance and user autonomy erosion are widesprea…
The paper introduces a generalized zero-shot benchmark for facial age estimation that ethically excludes children's data during training, demonstrating that current state-of-the-art models fail signif…
The paper introduces the Sovereign Context Protocol (SCP), an open-source, attribution-aware data access layer designed to standardize how Large Language Models (LLMs) connect to and track usage of hu…
This paper investigates privacy risks associated with credential disclosure in the upcoming EU Digital Identity Wallet, demonstrating that users tend to overshare information, and proposes a Credentia…
The paper introduces 'contrastive privacy,' a formal, model-agnostic, and quantitative method for evaluating the semantic success of AI-based sanitization across multiple media modalities.
KidsNanny is a two-stage multimodal content moderation pipeline that achieves high accuracy and efficiency in detecting child safety threats, particularly excelling in text-embedded content.
The paper introduces the concept of 'authenticity debt'—the institutional liability from deploying unverified AI content—and proposes a layered reference architecture combining cryptographic provenanc…
The paper introduces the concept of 'authenticity debt'—the institutional liability from deploying unverified AI content—and proposes a layered reference architecture combining cryptographic provenanc…
The paper proposes a privacy-preserving visual monitoring system that performs object detection and generates natural language alerts entirely on an edge device, ensuring GDPR compliance by never tran…
The paper introduces PHTV-Scout, a novel framework that analyzes Douyin and Kwai data, revealing a high prevalence of potentially harmful teen videos, particularly CSE imagery, and demonstrating that…
This study proposes a negotiation framework, using composite indices (RBTI and CATI), to explain how youth navigate competing privacy pressures when using smart voice assistants, finding that high usa…
Aegon is a new protocol that provides an auditable, tamper-evident infrastructure for tracking AI content licensing transactions and compliance receipts.
The paper proposes an on-device framework to detect and prevent the forwarding of images that have been physically recaptured (photographed) from a mobile screen, addressing the Screen Recaptured Anal…
The paper introduces MolTrust, a production-deployed trust infrastructure built on W3C standards (VCs and DIDs) that provides a verifiable, multi-layered authorization framework for autonomous AI agen…
Xinlei Guan, David Arosemena, Tejaswi Dhandu, Kuan Huang +6 more
The paper proposes an end-to-end forensic pipeline using steganographic attribution and multimodal harm detection to reliably trace and attribute harmful misuse of AI-generated imagery on social platf…
This paper conducts an independent security analysis of the C2PA specifications and concludes that the current system fails to meet its claimed security and necessary functional goals, making it unrel…
BIDO introduces a device-free, NIST AAL2-compliant biometric authentication standard that deterministically generates ephemeral ECDSA keys from live biometric measurements, eliminating the need for st…
The paper evaluates web tracking across ten countries, finding that opt-in jurisdictions (like the EU) generally enforce stronger privacy protections, significantly reducing tracker connections compar…
The paper proposes and proves the security of a generic, full end-to-end credential revocation system for European Digital Identity Wallets, relying on a single server and secure channels.
This study analyzed the online exposure of Thai National Identification Numbers and other sensitive personal data, revealing over 1.2 million records, primarily originating from government websites, w…