SearcharxivSearch

arXiv subjects

Z. M. Ma

Publications and source records attributed to Z. M. Ma.

2 recordsLinked to original sources

FraudSMSWalker: Benchmarking Agentic Large Language Models for SMS-to-Webpage Fraud Detection

SMS fraud is increasingly cross-channel: a message directs the user to a webpage, and the final risk depends on how the SMS claim aligns with the page content and requested user action. However, existing evaluations either focus on message-only smishing classification or expose URL and domain cues that allow models to rely on reputation shortcuts. To address this gap, we introduce \textbf{FraudSMSWalker}, a controlled benchmark for URL-masked SMS-to-webpage fraud judgment. FraudSMSWalker contains 699 bilingual chains, including 332 fraudulent and 367 benign cases, across ten service scenarios. The model-visible input consists of the SMS context and sanitized webpage evidence, while raw URLs, hosts, domains, IPs, redirects, and reputation metadata are withheld. The benchmark further includes hard benign cases whose pages contain login, payment, verification, or account-management elements that are plausible under the service context but also appear in scam flows. We evaluate nine web agents under masked browser-agent protocols and conduct URL-visibility ablations. The results show that current agents can detect suspicious cues, but struggle to preserve benign recall and often produce positive predictions that are weakly supported by the observed evidence. These findings position FraudSMSWalker as a benchmark for measuring whether web agents can make fraud judgments that remain both accurate and evidence-grounded when direct reputation shortcuts are suppressed. The associated code and dataset are accessible at the \href{https://anonymous.4open.science/w/FraudMessageWalker-Bench}{anonymous link}.

cs.CL

Superconductivity in LiFeO2Fe2Se2 with anti-PbO-type Spacer Layers

Superconductivity has been found in the iron-arsenides with different structures by alternative stacking of the conducting Fe2As2 layers and spacer layers including alkali- or alkali-earth metal ions and PbO- or perovskite-type oxides blocks. So far, no spacer layer could be intercalated in between the neutral Fe2Se2 layers similar in structure to Fe2As2 layers except for alkali-metal ions in AxFe2-ySe2. The superconducting phase in AxFe2-ySe2 with transition temperature of 32 K is always inter-grown with the insulating phase which exhibits an antiferromagnetic order with extremely high Neel temperature of ~560 K and the order of Fe vacancies. Such inhomogeneity makes the investigation on the underlying physics in AxFe2-ySe2 complicated. Here we report the synthesis of a novel superconductor LiFeO2Fe2Se2 by hydrothermal method, exhibiting superconductivity at ~43 K, in which anti-PbO-type spacer layers of LiFeO2 have been successfully intercalated between anti-PbO-type Fe2Se2 layers. This finding demonstrates that superconductivity can be realized in the iron selenide with a novel spacer layer of anti-PbO-type, which is not found in the iron arsenides, and expands the category of the iron-based superconductors. Such a new synthetic method paves a new way to search for possible novel superconductors with different spacer layers, which is helpful to further study the underlying physics in iron-based high-Tc superconductors.

cond-mat.supr-con