arXiv subjects

Sediola Ruko

Publications and source records attributed to Sediola Ruko.

3 recordsLinked to original sources

arXiv2026

KeHoSu: Keyed Homoglyph Substitution for Authenticated Text Provenance over Copy-Paste Channels

Nowadays, large language models produce text at scale, and much of it is redistributed across platforms. A moderator who finds a suspicious comment, post or article may want to know which platform generated it and for which account. In this paper we study attribution over the channel through which such text actually travels, copy-paste, which discards document metadata but keeps Unicode code points. We present KeHoSu, which turns the confusable characters of homoglyph attacks into a keyed attribution channel: the variant chosen for each carrier letter encodes one bit of an identifier made of a platform field, a user field and a truncated authentication tag. Moreover, given that reshared text is often quoted in fragments, and the placement therefore keeps no positional state, we show that KeHoSu is invariant to sentence reordering up to a constant boundary layer and depends on a partial quotation only through the retained length. We characterize the code-point channel by its capacity, removability and detectability, and provide an achievable region that relates the three. We evaluate KeHoSu over a wide range of use cases and show that the mark survived copy-paste across 18 common platforms, attributing the majority of all excerpts to the correct account at 178 letters (about two sentences) on LLM-generated stories and 167 letters (about one sentence) on standard English prose.

cs.CR↗

arXiv2026

Customized Tourist Navigation in Urban Contexts Following General Trends and Individual Preferences

Navigating an unfamiliar city poses significant challenges, and tourists are among the groups more likely to experience them, particularly when attempting to locate a point of interest (POI). Various factors, such as language barriers or a lack of precise information, further complicate this issue by making it difficult for visitors to explore efficiently. To address these issues, we introduce the tool "Personalized Assistant for Tourist Hints" (PATH), which is based on a methodology for estimating personalized tourist routes. PATH computes optimal paths to specified locations guided by two tailored heuristics: tourist frequency and POI preference. This integration enables efficient and personalized navigation, guiding users toward attractions that best match their preferences. We evaluated our methodology through a case study in Viterbo, Italy, using a dataset comprising over 1000 routes from 265 tourists who visited the city during different periods. To validate our approach, we tested it with 238 new tourists and collected expert assessments from 86 local specialists. User satisfaction was measured through a structured questionnaire, which revealed highly positive feedback regarding the relevance and quality of the recommended routes, also when compared with existing routing applications and approaches proposed in the literature. These results demonstrate PATH's potential to enhance urban exploration by providing an adaptable and user-centric solution for tourist navigation.

cs.HC↗

arXiv2025

Do You Trust Your Model? Emerging Malware Threats in the Deep Learning Ecosystem

Training high-quality deep learning models is a challenging task due to computational and technical requirements. A growing number of individuals, institutions, and companies increasingly rely on pre-trained, third-party models made available in public repositories. These models are often used directly or integrated in product pipelines with no particular precautions, since they are effectively just data in tensor form and considered safe. In this paper, we raise awareness of a new machine learning supply chain threat targeting neural networks. We introduce MaleficNet 2.0, a novel technique to embed self-extracting, self-executing malware in neural networks. MaleficNet 2.0 uses spread-spectrum channel coding combined with error correction techniques to inject malicious payloads in the parameters of deep neural networks. MaleficNet 2.0 injection technique is stealthy, does not degrade the performance of the model, and is robust against removal techniques. We design our approach to work both in traditional and distributed learning settings such as Federated Learning, and demonstrate that it is effective even when a reduced number of bits is used for the model parameters. Finally, we implement a proof-of-concept self-extracting neural network malware using MaleficNet 2.0, demonstrating the practicality of the attack against a widely adopted machine learning framework. Our aim with this work is to raise awareness against these new, dangerous attacks both in the research community and industry, and we hope to encourage further research in mitigation techniques against such threats.

cs.CR↗