The deployment of Machine-Generated Text (MGT) detection systems necessitates processing sensitive user data, creating a fundamental conflict between authorship verification and privacy preservation. Standard anonymization techniques often disrupt linguistic fluency, while rigorous Differential Privacy (DP) mechanisms typically degrade the statistical signals required for accurate detection. To resolve this dilemma, we propose textbf{DP-MGTD}, a framework incorporating an Adaptive Differentially Private Entity Sanitization algorithm. Our approach utilizes a two-stage mechanism that performs noisy frequency estimation and dynamically calibrates privacy budgets, […]

Ver mais

India AI Impact Summit 2026 is in full swing. Many delegates and tech leaders from across the world have landed in the capital city of India. Speaking of tech leaders, Google CEO Sundar Pichai, OpenAI CEO Sam Altman, Anthropic’s CEO, and many others have marked their presence in a marquee AI event. Bill Gates unexpectedly skips India AI Impact Summit keynote As far as Microsoft is concerned, Bill Gates also landed in India. The Microsoft co-founder, however, has […]

Ver mais

arXiv:2602.22847v1 Announce Type: cross Abstract: The concept of ranking aggregation plays a central role in preference analysis, and numerous algorithms for calculating median rankings, often originating in social choice theory, have been documented in the literature, offering theoretical guarantees in a centralized setting, i.e., when all the ranking data to be aggregated can be brought together in a single computing unit. For many technologies (e.g. peer-to-peer networks, IoT, multi-agent systems), extending the ability to calculate consensus rankings with […]

Ver mais

Part 1. Hybrid Solution for Dynamic Vehicle Routing — Context and Architecture The post A Generalizable MARL-LP Approach for Scheduling in Logistics appeared first on Towards Data Science.

Ver mais

arXiv:2603.02344v1 Announce Type: new Abstract: We present a passivity-agnostic framework for distributed adaptive synchronization under position-only communication, bounded disturbances, and unknown leader dynamics. By passivity-agnostic we mean the design does not require the closed loop system to be strictly positive real (SPR) a priori: it certifies SPR when present and recovers it by frequency shaping when absent. Followers are heterogeneous second-order systems with unknown (possibly unstable) dynamics. In the SPR regime, a structured reparameterization yields gradient-based adaptive error […]

Ver mais

arXiv:2601.15301v1 Announce Type: new Abstract: The rapid adoption of LLMs has increased the need for reliable AI text detection, yet existing detectors often fail outside controlled benchmarks. We systematically evaluate 2 dominant paradigms (training-free and supervised) and show that both are brittle under distribution shift, unseen generators, and simple stylistic perturbations. To address these limitations, we propose a supervised contrastive learning (SCL) framework that learns discriminative style embeddings. Experiments show that while supervised detectors excel in-domain, they degrade […]

Ver mais

In the U.S. digital economy, small and medium-sized businesses (SMBs) and creators in remote regions face structural disadvantages in access to integrated advertising and incentive platforms, largely due to accelerating privacy regulations and the fragmentation of cross channel datasets. This paper proposes a unified federated and differentially private measurement framework that integrates Topics/Protected Audience, Attribution Reporting, and SKAdNetwork, aiming to achieve privacy-preserving incentive optimization and cross-channel effectiveness measurement for web and mobile environments. The framework prioritizes compliant data […]

Ver mais