digitado

arXiv:2604.18722v1 Announce Type: new Abstract: Cross-lingual transfer in NLP is often hindered by the “script barrier” where differences in writing systems inhibit transfer learning between languages. Transliteration, the process of converting the script, has emerged as a powerful technique to bridge this gap by increasing lexical overlap. This paper provides a comprehensive survey of the application of transliteration in cross-lingual NLP. We present a taxonomy of key motivations to utilize transliterations in language models, and provide an overview […]

Ver mais

arXiv:2604.18718v1 Announce Type: new Abstract: Agentic security systems increasingly audit live targets with tool-using LLMs, but prior systems fix a single coordination topology, leaving unclear when additional agents help and when they only add cost. We treat topology choice as an empirical systems question. We introduce a controlled benchmark of 20 interactive targets (10 web/API and 10 binary), each exposing one endpoint-reachable ground-truth vulnerability, evaluated in whitebox and blackbox modes. The core study executes 600 runs over five […]

Ver mais

arXiv:2604.18717v1 Announce Type: new Abstract: Formal verification of masking in post-quantum cryptographic (PQC) hardware relies on SMT solvers over finite domains. Our prior work established structural dependency analysis at scale [1] and quantified the security margin of partial NTT masking [2]. QANARY, our structural dependency analysis framework, verified 1.17 million cells across 30 modules of the Adams Bridge ML-DSA/ML-KEM accelerator [3, 4], but its core soundness result (Theorem 3.9.1) was machine-checked only at $q = 5$ via $2^{25}$ […]

Ver mais

arXiv:2604.18716v1 Announce Type: new Abstract: Today, machine learning is widely applied in sensitive, security-related, and financially lucrative applications. Model extraction attacks undermine current business models where a model owner sells model access, e.g., via MLaaS APIs. Additionally, stolen models can enable powerful white-box attacks, facilitating privacy attacks on sensitive training data, and model evasion. In this paper, we focus on Decision Trees (DT), which are widely deployed in practice. Existing black-box extraction attacks for DTs are either query-intensive, […]

Ver mais

arXiv:2604.18715v1 Announce Type: new Abstract: Earth observation foundation models encode land surface information into dense embedding vectors, yet the geometric structure of these representations and its implications for downstream reasoning remain underexplored. We characterize the manifold geometry of Google AlphaEarth’s 64-dimensional embeddings across 12.1 million Continental United States samples (2017–2023) and develop an agentic system that leverages this geometric understanding for environmental reasoning. The manifold is non-Euclidean: effective dimensionality is 13.3 (participation ratio) from 64 raw dimensions, with […]

Ver mais

arXiv:2604.18713v1 Announce Type: new Abstract: Automated 3D segmentation of prostate lesions from biparametric MRI (bp-MRI) is essential for reliable algorithmic analysis, but achieving high precision remains challenging. Volumetric methods must combine multiple modalities while ensuring anatomical consistency, but current models struggle to integrate cross-modal information reliably. While vision-language models (VLMs) are replacing the currently used architectural designs, they still lack the fine-grained, lesion-level semantics required for effective localized guidance. To address these limitations, we propose a new multi-encoder […]

Ver mais

arXiv:2604.18712v1 Announce Type: new Abstract: Probing has shown that language model representations encode rich linguistic information, but it remains unclear whether they also capture cognitive signals about human processing. In this work, we probe language model representations for human reading times. Using regularized linear regression on two eye-tracking corpora spanning five languages (English, Greek, Hebrew, Russian, and Turkish), we compare the representations from every model layer against scalar predictors — surprisal, information value, and logit-lens surprisal. We find […]

Ver mais

arXiv:2604.18698v1 Announce Type: new Abstract: Real-world graph applications are generally larger than the size of the cache itself. Due to this reason, the memory hierarchy was identified as a key bottleneck by the earlier works. Undoubtedly, the performance can be achieved by improving cache, there is still a scope for performance gain by improving branch prediction accuracy. In graph processing applications, the occurrence of branch mispredictions is very frequent and is a major limitation for the overall performance. […]

Ver mais

arXiv:2604.18697v1 Announce Type: new Abstract: Indistinguishability properties such as differential privacy bounds or low empirically measured membership inference are widely treated as proxies to show a model is sufficiently protected against broader memorization risks. However, we show that indistinguishability properties are neither sufficient nor necessary for preventing data extraction in LLM APIs. We formalize a privacy-game separation between extraction and indistinguishability-based privacy, showing that indistinguishability and inextractability are incomparable: upper-bounding distinguishability does not upper-bound extractability. To address this […]

Ver mais

arXiv:2604.18667v1 Announce Type: new Abstract: We present linear-space data structures for several frequency queries on trees, namely: path mode, path least frequent element, and path $alpha$-minority queries. We present the first linear-space data structures, requiring $O(n sqrt{nw})$ preprocessing time, that can answer path mode and path least frequent element queries in $O(sqrt{n/w})$ time. This improves upon the best previously known bound of $O(loglog n sqrt{n/w})$ achieved by Durocher et al. in 2016. For the path $alpha$-minority problem, where […]

Ver mais