Anomalous Behavior Research Articles

Anomalous Behavior Detection in Trajectory Data of Older Drivers.

Given a road network and a set of trajectory data, the anomalous behavior detection (ABD) problem is to identify drivers that show significant directional deviations, hard-brakings, and accelerations in their trips. The ABD problem is important in many societal applications, including Mild Cognitive Impairment (MCI) detection and safe route recommendations for older drivers. The ABD problem is computationally challenging due to the large size of temporally-detailed trajectories dataset. In this paper, we propose an Edge-Attributed Matrix that can represent the key properties of temporally-detailed trajectory datasets and identify abnormal driving behaviors. Experiments using real-world datasets demonstrated that our approach identifies abnormal driving behaviors.

Fractional derivative method for anomalous aquitard flow in a leaky aquifer system with depth-decaying aquitard hydraulic conductivity

Aquitards significantly affect groundwater flow in multi-aquifer systems through adjacent aquifer leakage. Despite this, studies focusing on their heterogeneity and the non-conventional diffusion patterns of their flow are still limited. In this study, a factional derivative approach was first extended to explore the time-dependent behavior of flow transport in the aquitard. Two analytical solutions were derived for specific discharges in independent aquitards under different boundary conditions. The findings revealed that aquitard flow exhibits obvious anomalous diffusion behaviors, characterized by slower decay and heavy-tailed specific discharge data. The fractional derivative model provided a more accurate representation of this behavior than traditional models, as evidenced by its superior agreement with experimental data. Moreover, a transient model for pumping tests in a leaky aquifer system was developed, incorporating the memory effect of anomalous flow and vertical heterogeneity in aquitards. Relevant semi-analytical solutions were derived to explore the impacts of memory factor β and decay exponent of aquitard hydraulic conductivity (K) on the leakage aquifer system. Theoretical results demonstrated that stronger memory effect reduces drawdowns in the aquitard and confined aquifer during mid-to-late times. A larger dimensionless decay exponent (Ad) decreases aquitard drawdown and increases aquifer drawdown at late times. Sensitivity analysis showed aquitard drawdown experiences two peaks in sensitivity to β and Ad at early- or mid-times, affected by memory effect and decay exponent of aquitard K, signifying maximal impact at these specific intervals. This study provides a practical model to effectively manage groundwater resources by accurately reflecting aquitard memory and heterogeneity effects.

IoT Botnet Detection Based on Anomalies of Multiscale Time Series Dynamics

In this work, we propose a solution for detecting botnet attacks in the Internet of Things (IoT) by identifying anomalies in the temporal dynamics of their devices. Given their limited computing capabilities, IoT devices are more vulnerable to attacks than conventional computers. In this scenario, botnets have a high degree of severity since they are used to trigger distributed denial-of-service attacks, which are amplified by a large number of IoT devices. Thus, solutions aiming to identify and mitigate the damage caused by botnets in IoT are urgent and essential. We evaluate the number of packets a device transmits, following a multiscale ordinal patterns transformation, and uses Isolation Forest for anomaly detection. By investigating how devices evolve, we can distinguish between normal and anomalous behaviors. We apply the proposed solution to detect two major botnets for IoT: Mirai and Bashlite. We evaluated our model throughout two experimental setups. The first, using a single model for all devices, reaching 99.5% of accuracy and 99.6% of specificity, and the second, by tuning a model per device, reaching 100% of accuracy. These results show that, with the proper transformation, it is possible to use simple methods for detecting anomalies in IoT devices' behaviors.

AI SENTRY: REINVENTING CYBERSECURITY THROUGH INTELLIGENT THREAT DETECTION

In recent years, the escalating complexity and frequency of cyber threats have presented a formidable challenge to traditional cybersecurity measures. The emergence of artificial intelligence (AI) technologies has revolutionized the landscape, offering a promising solution to fortify defenses against evolving threats. This paper introduces AI Sentry, an innovative approach to cybersecurity that leverages the power of AI for intelligent threat detection and prevention. AI Sentry embodies a paradigm shift in cybersecurity, integrating machine learning, neural networks, and advanced algorithms to proactively identify, analyze, and mitigate potential threats in real time. By continuously learning from vast datasets and adapting to new attack vectors, AI Sentry enhances its ability to recognize anomalous patterns and behaviors, thereby thwarting sophisticated cyber assaults. The core strength of AI Sentry lies in its capability to detect anomalies and predict threats with a high degree of accuracy, surpassing the limitations of traditional signature-based systems. Through anomaly detection, behavioral analysis, and contextual understanding, AI Sentry not only identifies known threats but also anticipates zero-day attacks and previously unseen malicious activities. This paper delves into the technical underpinnings of AI Sentry, elucidating its architecture, data processing techniques, machine learning models, and the orchestration of various AI components. Furthermore, it explores the ethical considerations and challenges associated with AI-powered cybersecurity, including issues of privacy, bias mitigation, and transparency in decision-making.

Hysteresis Phenomena in a Liquid Sessile Drop on a Stretchable Inclined Elastic Substrate

The authors studied states of liquid sessile drops on a stretchable inclined elastic substrate to find out peculiarities of the contact angles hysteresis by digital optical microscopes. The drop elongation and contact angles were recorded on the stages of the band stretching and contraction. An anomalous behavior of the drop was found on the first step of the contraction during which the measured drop parameters remained unchanged. Finally, a new hydrophysical effect was found. It is hysteresis of the drop states, on the background of which the contact angle hysteresis exists.

Anomalous field-temperature phase diagram of superconductivity in Sn–Pb solder

Sn–Pb solders are superconducting materials whose Sn and Pb are perfectly phase-separated. Recently, anomalous magnetic-flux trapping in a Sn45–Pb55 solder has been revealed, where the magnetic fluxes are selectively trapped in the Sn regions due to the supercurrents in the surrounding Pb regions. Here, we report on the observation of the anomalous critical field (Hc)-temperature (T) phase diagram of superconductivity in the Sn45–Pb55 solder. Although the Hc(T) for the Pb regions decreases with increasing field as in normal type-I superconductors and is consistent with the conventional trend with Hc(0) ∼ 800 Oe, the Hc(T) for the Sn regions exhibits anomalous behaviors. The most noticeable trend was observed in the field-cooled (under 1500 Oe) solder. The Hc-T phase diagram for the Sn regions largely varies when the applied external field is reversed, and Tc increases with increasing field amplitude when H < 0 Oe is applied. On the basis of the flux trapping and the observed anomalous Hc-T phase diagrams, we propose that the field-robust superconductivity in the Sn regions is related to the ferromagnetically aligned magnetic fluxes (or formation of vortices) in the Sn regions of the Sn45–Pb55 solder.

Adversarial Data Augmentation for HMM-based Anomaly Detection.

In this work, we concentrate on the detection of anomalous behaviors in systems operating in the physical world and for which it is usually not possible to have a complete set of all possible anomalies in advance. We present a data augmentation and retraining approach based on adversarial learning for improving anomaly detection. In particular, we first define a method for generating adversarial examples for anomaly detectors based on Hidden Markov Models (HMMs). Then, we present a data augmentation and retraining technique that uses these adversarial examples to improve anomaly detection performance. Finally, we evaluate our adversarial data augmentation and retraining approach on four datasets showing that it achieves a statistically significant performance improvement and enhances the robustness to adversarial attacks. Key differences from the state-of-the-art on adversarial data augmentation are the focus on multivariate time series (as opposed to images), the context of one-class classification (in contrast to standard multi-class classification, and the use of HMMs (in contrast to neural networks).

Dynamical localization and slow thermalization in a class of disorder-free periodically driven one-dimensional interacting systems

We study if the interplay between dynamical localization and interactions in periodically driven quantum systems can give rise to anomalous thermalization behavior. Specifically, we consider one-dimensional models with interacting spinless fermions with nearest-neighbor hopping and density-density interactions, and a periodically driven on-site potential with spatial periodicity m=2 and m=4. At a dynamical localization point, these models evade thermalization either due to the presence of an extensive number of conserved quantities (for weak interactions) or due to the kinetic constraints caused by drive-induced resonances (for strong interactions). Our models therefore illustrate interesting mechanisms for generating constrained dynamics in Floquet systems which are difficult to realize in an undriven system.

Exploring complex magnetic phase transitions and magnetocaloric effect in the nanocrystalline Nd0.5Ca0.5MnO[formula omitted] compound

In this article, we have investigated the temperature and magnetic field-induced complex magnetic phases and magnetocaloric properties of the nanocrystalline Nd0.5Ca0.5MnO3 (NCMO) compound in detail. The compound exhibits charge-ordered antiferromagnetic (CO-AFM) and charge-orbital-ordered antiferromagnetic (AFM) phases at TCO≃ 225 K and TN= 160 K respectively. At the intermediate temperature range, i.e. TN≤ T ≤ TCO, an unfamiliar magnetic state is present where the orbital ordering of manganese ions sets progressively. Both the short-range and zig-zag ordered ferromagnetic (FM) chains and an AFM phase coexist within this temperature window. The effect of magnetic field and temperature drastically modifies the fragile magnetic ground state and this change is also reflected in the magnetocaloric properties of the studied compound. At the low-temperature region, an inverse magnetocaloric effect (MCE) is noticed due to the kinetically arrested magnetic moments of the AFM phase. However, a conventional MCE is noticed in the high-temperature regime. The anomalous behavior of the MCE in the nanocrystalline NCMO compound is analyzed by considering the effect of the reduction of particle size and the meta-stable nature of the magnetic ground state. In addition, we have paid attention to the hysteretic losses associated with the first-order phase transition (FOPT) in order to estimate the magnetic cooling capacity for the material. These studies carry notable importance for the usefulness of nanocrystalline half-doped manganite compounds not only for basic scientific research purpose, but also having possible practical utilization in the magnetic refrigeration industries.

Multi-Objective Seagull Optimization Algorithm with Deep Learning-Enabled Vulnerability Detection for Secure Cloud Environments

Cloud computing (CC) is an internet-enabled environment that provides computing services such as networking, databases, and servers to clients and organizations in a cost-effective manner. Despite the benefits rendered by CC, its security remains a prominent concern to overcome. An intrusion detection system (IDS) is generally used to detect both normal and anomalous behavior in networks. The design of IDS using a machine learning (ML) technique comprises a series of methods that can learn patterns from data and forecast the outcomes consequently. In this background, the current study designs a novel multi-objective seagull optimization algorithm with a deep learning-enabled vulnerability detection (MOSOA-DLVD) technique to secure the cloud platform. The MOSOA-DLVD technique uses the feature selection (FS) method and hyperparameter tuning strategy to identify the presence of vulnerabilities or attacks in the cloud infrastructure. Primarily, the FS method is implemented using the MOSOA technique. Furthermore, the MOSOA-DLVD technique uses a deep belief network (DBN) method for intrusion detection and its classification. In order to improve the detection outcomes of the DBN algorithm, the sooty tern optimization algorithm (STOA) is applied for the hyperparameter tuning process. The performance of the proposed MOSOA-DLVD system was validated with extensive simulations upon a benchmark IDS dataset. The improved intrusion detection results of the MOSOA-DLVD approach with a maximum accuracy of 99.34% establish the proficiency of the model compared with recent methods.

High Temperature Tensile Properties and Microstructure of Ni20Cr Alloy Fabricated by Laser Powder Bed Fusion

Additive Manufacturing (AM) brings about an array of modifications in microstructure with respect to conventional routes transforming mechanical performances. These new microstructure features depend on process parameters and especially on volume energy-density delivered by the laser on powder layer. Among the different alloys manufactured by AM, Ni-alloys exhibit high-strength at elevated temperature opening the way of fabrication of gas turbines and jet-engine parts. Ni-superalloys experience precipitation hardening due to the formation of γ′ and γ′′ phases leading to complex microstructures. To better study the influence of the AM microstructure on Ni-alloys mechanical properties, in particular at elevated temperatures, a theoretically monophasic and binary Ni20Cr-alloy manufactured by laser powder-bed fusion was studied in this work. Remarkable Yield Strength (400 MPa) and Ultimate Tensile Strength (UTS) (600 MPa) were observed at 500°C with hardly any loss of properties from room temperature, owing to the thermal stability of cellular dendrites till 700°C. Ductility drop was reported at 700°C due to anomalous brittle behaviour of Ni-alloys. Hardening behaviour vanished at 900°C signifying the deletion of dendrites, disappearance of dislocations, diffusion of Cr from dendritic walls and growth of oxides.

Extrinsic anomalous Hall effect in Mn doped GeSnTe semiconductors in the bad-metal hopping regime

We present high field magnetotransport studies of Ge1-x-y(SnxMny)Te bulk multiferroics with diamagnetic Sn and paramagnetic Mn concentration, 0.38 ≤ x ≤ 0.79 and 0.02 ≤ y ≤ 0.086, respectively. The zero-field resistivity, ρxx(T) takes significant contribution from defects below T ≤ 20 K however; a mixed scattering contribution from phonons and unusual sources is estimated from T ≈ 20–300 K. The carrier mobility shows anomalous temperature dependence from ∼T–0.2 to ∼T–0.5 which hints towards possible presence of polaronic effects resulting from coupling of holes with phonons. This anomalous behavior cannot be understood in terms of pure phononic scattering mechanism at high temperatures. From point of view of high magnetic field results, the transverse component of magneto-resistivity manifests anomalous Hall effect originating from extrinsic scattering sources, particularly the side jump mechanism reveals a dominating contribution. We also find that the correlation between the transverse and longitudinal conductivities follow the universal scaling law σxy ∼ σxxn where n = 1.6 in the low conductivity limit. The values n = 1.5 – 1.8 obtained for the present Ge1-x-y(SnxMny)Te alloys justify the bad-metal hopping regime of our crystals since the results fall in the low conductivity ferromagnetic family with σxx ≤ 104 (Ω cm)–1. The interpretation of the n = 1.6 scaling in the low conductivity regime is thus far not fully understood. However; the anomalous Hall resistivity scaling with modified relation by Tian et al., is indicative of the dominant side jump scattering along with noticeable role of skew scattering.

Structural and vibrational properties of cage-type Sc5Ru6Sn18 superconductor under pressure using synchrotron X-ray diffraction and Raman spectroscopy

We report detailed structural investigations of cage-type quasi-skutterudite compound Sc5Ru6Sn18 using synchrotron single-crystal and powder x-ray diffraction. Single-crystal x-ray diffraction studies at ambient temperature revealed that the Sc5Ru6Sn18 compound has a tetragonal symmetry in the I41/acd space group setting with a = 13.58Å and c = 27.14Å, similar to other R5Rh6Sn18 (R = Y, Sc, Lu) cage-type compounds. The electrical resistivity ρ(T) revealed the presence of a sharp superconducting (SC) transition at Tc = 4.07K. The ρ(T) of Sc5Ru6Sn18 above Tc shows a smooth decrease with decreasing temperature without any evident anomalies. Systematic temperature dependent synchrotron x-ray powder diffraction (XRPD) studies covering 400 to 110K shows that the Sc5Ru6Sn18 system remain in the tetragonal I41/acd structure in this temperature range without any anomalous behaviour in the unit-cell parameters. High-pressure (HP) synchrotron XRPD revealed a smooth reduction in the unit-cell parameters up to ~7GPa which can be well described by a third-order Birch-Murnaghan equation providing the bulk modulus of the system to be ~102.6GPa. This system is found to several Raman modes below 300cm-1. We could follow the pressure evolution of four Raman modes, all of which show a smooth hardening with pressure up to ~7GPa. Our results call for systematic HP studies of the SC properties of the title system.

Dzyaloshinsky–Moriya Interaction Induced Anomalous g Behavior of Sr2IrO4 Probed by Electron Spin Resonance

Among the 5d transition metal iridates, Sr2IrO4, which has a layered chalcogenide structure, has received much attention due to its strong spin–orbit coupling (SOC), which produces Mott insulating states and anomalous physical behaviors. In this paper, the microscopic magnetism of Sr2IrO4 is studied with electron spin resonance (ESR) measurements. The Lande factor g of the ferromagnetic resonance signal of Sr2IrO4 shows anomalous behavior compared to typical ferromagnets. It gradually decreases, and the corresponding resonance field Hr increases, with decreasing temperature. The various physical parameters. including the saturated magnetic field Hs derived from M-H, Hr, ΔHpp, the g factor and the intensity I extracted from ESR spectra, are analyzed in detail. Eventually, it is revealed that the anomalous behavior of the g-factor is induced by in-plane Dzyaloshinsky–Moriya interaction (DMI) rather than the SOC effect.

Critical dynamics of long-range quantum disordered systems.

Long-range hoppings in quantum disordered systems are known to yield quantum multifractality, the features of which can go beyond the characteristic properties associated with an Anderson transition. Indeed, critical dynamics of long-range quantum systems can exhibit anomalous dynamical behaviors distinct from those at the Anderson transition in finite dimensions. In this paper, we propose a phenomenological model of wave packet expansion in long-range hopping systems. We consider both their multifractal properties and the algebraic fat tails induced by the long-range hoppings. Using this model, we analytically derive the dynamics of moments and inverse participation ratios of the time-evolving wave packets, in connection with the multifractal dimension of the system. To validate our predictions, we perform numerical simulations of a Floquet model that is analogous to the power law random banded matrix ensemble. Unlike the Anderson transition in finite dimensions, the dynamics of such systems cannot be adequately described by a single parameter scaling law that solely depends on time. Instead, it becomes crucial to establish scaling laws involving both the finite size and the time. Explicit scaling laws for the observables under consideration are presented. Our findings are of considerable interest towards applications in the fields of many-body localization and Anderson localization on random graphs, where long-range effects arise due to the inherent topology of the Hilbert space.

Anomalous behavior recognition of underwater creatures using lite 3D full-convolution network

Global warming and pollution could lead to the destruction of marine habitats and loss of species. The anomalous behavior of underwater creatures can be used as a biometer for assessing the health status of our ocean. Advances in behavior recognition have been driven by the active application of deep learning methods, yet many of them render superior accuracy at the cost of high computational complexity and slow inference. This paper presents a real-time anomalous behavior recognition approach that incorporates a lightweight deep learning model (Lite3D), object detection, and multitarget tracking. Lite3D is characterized in threefold: (1) image frames contain only regions of interest (ROI) generated by an object detector; (2) no fully connected layers are needed, the prediction head itself is a flatten layer of 1 × {mathcal{l}} @ 1× 1, {mathcal{l}}= number of categories; (3) all the convolution kernels are 3D, except the first layer degenerated to 2D. Through the tracking, a sequence of ROI-only frames is subjected to 3D convolutions for stacked feature extraction. Compared to other 3D models, Lite3D is 50 times smaller in size and 57 times lighter in terms of trainable parameters and can achieve 99% of F1-score. Lite3D is ideal for mounting on ROV or AUV to perform real-time edge computing.

Li–Pd–Rh-D2O electrochemistry experiments at elevated voltage

In 2013, the U.S. Navy disclosed an electrochemistry procedure intended to produce MeV-energy nuclear particles, based on eV-energy electrical inputs, which may be indicative of a new scientific phenomenon. This work is based on the 2013 disclosure and shows initial evidence validating the prior claims of nuclear particle generation. Additionally, several variations on the 2013 electrochemical recipe are made in order to find a highly repeatable recipe for future replications by other teams. The experiments described here produced dense collections of tracks in solid-state nuclear track detectors, radio frequency (RF) emissions, and anomalous heat flux, which are indicative of potential nuclear, or unusual chemical, reactions. Experimental results include tracks in solid-state nuclear track detectors similar in size to tracks produced by 4.7 MeV alpha particles on identical detectors exposed to radioactive Th-230; RF pulses up to 6 dB above the noise floor, which indicate that these signals were likely not background noise and not caused by known chemical reactions; and heat flux of 10 s of kJ, measured to 6σ significance, over and above input electrical energy, indicative of unknown exothermic reactions. Six out of six nuclear track detectors, utilized in experiments and interrogated for tracks post-experiment, produced positive results that our team attributes to thousands of individual particle impacts in dense clusters, likely with energies between 0.1 and 20 MeV. Similar nuclear particle, thermal, and RF results have separately appeared in prior reports, but in this work, all three categories of anomalous behavior are reported. Results indicate that the 2013 procedure may be a useful guide toward a set of highly repeatable reference experiments, showing initial but not overwhelming evidence of a new scientific phenomenon. Repeatable recipes are shared so that other groups may replicate and extend the present work.

A Fully Privacy-Preserving Solution for Anomaly Detection in IoT using Federated Learning and Homomorphic Encryption

AbstractAnomaly detection for the Internet of Things (IoT) is a very important topic in the context of cyber-security. Indeed, as the pervasiveness of this technology is increasing, so is the number of threats and attacks targeting smart objects and their interactions. Behavioral fingerprinting has gained attention from researchers in this domain as it represents a novel strategy to model object interactions and assess their correctness and honesty. Still, there exist challenges in terms of the performance of such AI-based solutions. The main reasons can be alleged to scalability, privacy, and limitations on adopted Machine Learning algorithms. Indeed, in classical distributed fingerprinting approaches, an object models the behavior of a target contact by exploiting only the information coming from the direct interaction with it, which represents a very limited view of the target because it does not consider services and messages exchanged with other neighbors. On the other hand, building a global model of a target node behavior leveraging the information coming from the interactions with its neighbors, may lead to critical privacy concerns. To face this issue, the strategy proposed in this paper exploits Federated Learning to compute a global behavioral fingerprinting model for a target object, by analyzing its interactions with different peers in the network. Our solution allows the training of such models in a distributed way by relying also on a secure delegation strategy to involve less capable nodes in IoT. Moreover, through homomorphic encryption and Blockchain technology, our approach guarantees the privacy of both the target object and the different workers, as well as the robustness of the strategy in the presence of attacks. All these features lead to a secure fully privacy-preserving solution whose robustness, correctness, and performance are evaluated in this paper using a detailed security analysis and an extensive experimental campaign. Finally, the performance of our model is very satisfactory, as it consistently discriminates between normal and anomalous behaviors across all evaluated test sets, achieving an average accuracy value of 0.85.

Weakly-Supervised Video Anomaly Detection with MTDA-Net

Weakly supervised anomalous behavior detection is a popular area at present. Compared to semi-supervised anomalous behavior detection, weakly-supervised learning both eliminates the need to crop videos and solves the problem of semi-supervised learning’s difficulty in handling long videos. Previous work has used graph convolution or self-attention mechanisms to model temporal relationships. However, these methods tend to model temporal relationships at a single scale and lack consideration of the aggregation problem for different temporal relationships. In this paper, we propose a weakly supervised anomaly detection framework, MTDA-Net, with emphasis on modeling different temporal relationships and enhanced semantic discrimination. To this end, we construct a new plug-and-play module, MTDA, which uses three branches, Multi-headed Attention (MHA), Temporal Shift (TS), and Dilated Aggregation (DA), to extract different temporal sequences. Specifically, the MHA branch can globally model the video information and project the features into different semantic spaces to enhance the expressiveness and discrimination of the features. The DA branch extracts temporal information of different scales via dilated convolution and captures the temporal features of local regions in the video. The TS branch can fuse the features of adjacent frames on a local scale and enhance the information flow. MTDA-Net can learn the temporal relationships between video segments on different branches and learn powerful video representations based on these relationships. The experimental results on the XD-Violence dataset show that MTDA-Net can significantly improve the detection accuracy of abnormal behaviors.

PATH-17. PILOCYTIC ASTROCYTOMA EXHIBITING DIFFUSE LEPTOMENINGEAL DISSEMINATION: EXTREMELY RARE FORM OF LOW-GRADE GLIOMA WITH DICHOTOMOUS (CHILDREN VERSUS ADULTS) AND UNCHARACTERISTICALLY AGGRESSIVE BEHAVIOR

Abstract OBJECTIVE To identify all prior reports of pilocytic astrocytoma (PA) exhibiting diffuse leptomeningeal dissemination (LMD) (WHO Grade I) in an effort to comprehensively characterize this anomalous, predominantly pediatric pathology. METHODS A systematic review of the literature was performed using the PubMed, Scopus, and Web of Science databases. RESULTS Twenty-nine studies featuring 60 patients (54 pediatric,6 adult) were identified.The mean age at initial diagnosis was 10.2 ± 10.6 years (range, 0.3 to 55 years), and most of the patients were male (n=39,65.0%). The most common primary tumor locations were the hypothalamus (n=18,30.0%), cerebellum (n=16,26.7%), and optic chiasm (n=8,13.3%). Signs/symptoms at presentation included paralysis, cerebellar findings, and symptomatic, obstructive hydrocephalus. Most patients underwent surgery alone (n=26,43.4%) or in combination with radiotherapy (n=10,16.7%) or chemotherapy (n=8,13.3%). Of 43 patients who underwent surgery, subtotal resection (STR) was achieved in 26. STR appeared to be a risk factor for future LMD and poor prognosis. Additionally, adjuvant therapy did not seem to reduce the odds of subsequent LMD. Twenty-two patients (36.7%) were found to have LMD at presentation. Time to dissemination for the remaining patients ranged from between 3.6 - 206 months. Among all the included patients, 24 (40%) exhibited LMD within the brain only, 22 (36.7%) within the spine only, and 14 (23.3%) within both locations. Multi-agent chemotherapy alone (n=20, 33.3%) was the most commonly utilized treatment modality, followed by radiotherapy alone (n=13,21.7%), surgery with radiotherapy (n=10,16.7%), and surgery alone (n=5,8.3%). The mean follow-up duration was 44.2 ± 47.7 months (range, 0 to 221 months). Mortality occurred in 18 out of the 58 patients who had follow-up information available, with a mean time from LMD diagnosis to death of 19.9 ± 23.6 months. CONCLUSION Given its truly anomalous behavior, future concerted efforts to analyze the genetic profile of all identified tissue samples of PA with LMD is warranted.