ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

~ similar to 2605.05513v1· 20 results

cs.CRRecentMar 23, 2026

When the Abyss Looks Back: Unveiling Evolving Dark Patterns in Cookie Consent Banners

Nivedita Singh, Seyoung Jin, Hyoungshick Kim

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…

View →
cs.CVcs.AIRecentMay 28, 2026

Toward Ethical Facial Age Estimation: A Generalized Zero-Shot Benchmark Without Training on Children's Data

Caio Petrucci, Leo Sampaio Ferraz Ribeiro, Sandra Avila

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…

View →
cs.CRcs.AIcs.LGRecentMar 28, 2026

Sovereign Context Protocol: An Open Attribution Layer for Human-Generated Content in the Age of Large Language Models

Praneel Panchigar, Torlach Rush, Matthew Canabarro

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…

View →
cs.CRRecentJun 4, 2026

Credential Disclosure in (EU) Digital Identity Wallets: Privacy Risks and Practical Mitigations

Sheila Zingg, Daniele Lain, Yoshimichi Nakatsuka, Kari Kostiainen +2 more

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…

View →
cs.CRRecentMay 3, 2026

Contrastive Privacy: A Semantic Approach to Measuring Privacy of AI-based Sanitization

George Bissias, Eugene Bagdasarian, Brian Neil Levine

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.

View →
cs.CVcs.CRRecentMar 17, 2026

KidsNanny: A Two-Stage Multimodal Content Moderation Pipeline Integrating Visual Classification, Object Detection, OCR, and Contextual Reasoning for Child Safety

Viraj Panchal, Tanmay Talsaniya, Parag Patel, Meet Patel

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.

View →
cs.CRcs.AIcs.CYRecentMay 30, 2026

Authenticity Debt and the Synthetic Content Threat Landscape: A Layered Framework for Trust, Provenance, and IP Governance in the Generative AI Era

Shubhashis Sengupta, Benjamin McCarty, Milind Savagaonkar, Rhine Andotra

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…

View →
cs.CRcs.AIcs.CYRecentMay 30, 2026

Authenticity Debt and the Synthetic Content Threat Landscape: A Layered Framework for Trust, Provenance, and IP Governance in the Generative AI Era

Shubhashis Sengupta, Benjamin McCarty, Milind Savagaonkar, Rhine Andotra

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…

View →
cs.CVcs.CRRecentMay 28, 2026

On-Device Generative AI for GDPR-Compliant Visual Monitoring: Natural Language Alerts from Local Object Detection

Gudrun Schappacher-Tilp, Nicoletta Kaehling, Jan Kornberger, Egon Teiniker

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…

View →
cs.CRcs.HCRecentMay 22, 2026

When Youth Enter the Algorithmic Wild: Discovering and Understanding Potentially Harmful Teen Videos on Douyin and Kwai

Shaoxuan Zhou, Yafei Sun, Jing Zhang, Xianghang Mi

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…

View →
cs.CRcs.AIcs.CYRecentApr 4, 2026

Negotiating Privacy with Smart Voice Assistants: Risk-Benefit and Control-Acceptance Tensions

Molly Campbell, Mohamad Sheikho Al Jasem, Ajay Kumar Shrestha

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…

View →
cs.CRcs.CYRecentApr 8, 2026

Aegon: Auditable AI Content Access with Ledger-Bound Tokens and Hardware-Attested Mobile Receipts

Amrish Baskaran, Nirbhay Pherwani, Raghul Krishnan

Aegon is a new protocol that provides an auditable, tamper-evident infrastructure for tracking AI content licensing transactions and compliance receipts.

View →
cs.CRRecentApr 14, 2026

Mitigating S-RAHA: An On-device Framework to Prevent Forwarding of Re-Captured Images

Keshav Sood, Iynkaran Natgunanathan, Purathani Praitheeshan, Praitheeshan Kirupananthan

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…

View →
cs.CRcs.AIRecentMay 7, 2026

From Specification to Deployment: Empirical Evidence from a W3C VC + DID Trust Infrastructure for Autonomous Agents

Lars Kersten Kroehl

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…

View →
cs.CVcs.AIcs.CRRecentApr 12, 2026

Toward Accountable AI-Generated Content on Social Platforms: Steganographic Attribution and Multimodal Harm Detection

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…

View →
cs.CRRecentApr 27, 2026

Verifying Provenance of Digital Media: Why the C2PA Specifications Fall Short

Enis Golaszewski, Neal Krawetz, Alan T. Sherman, Edward Zieglar +7 more

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…

View →
cs.ETcs.CRcs.CVRecentMay 16, 2026

BIDO: A Biometric Identity Online Authentication Framework

Aditya Mithra, Sibi Chakkaravarthy S, Srinivas Kankanala

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…

View →
cs.CRcs.CYRecentApr 18, 2026

Global Web, Local Privacy? An International Review of Web Tracking

Harry Yu, Patton Yin, Sebastian Zimmeck

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…

View →
cs.CRRecentMar 24, 2026

PRETTINESS -- Privacy pResErving aTTrIbute maNagEment SyStem

Jelizaveta Vakarjuk, Alisa Pankova

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.

View →
cs.CRcs.CYRecentApr 26, 2026

Analysis of Personal Data Exposure in Thailand

Suphannee Sivakorn, Sasawat Malaivongs, Nuttaya Rujiratanapat

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…

View →