Risk Of Leakage Research Articles

Risk assessment of gas plume dispersion in bunkering of alternative fuel through validated computational fluid dynamics approach

Abstract Maritime decarbonization is crucial in fighting climate change. Adopting low-carbon alternative fuels could help reduce greenhouse gas (GHG) emissions by 50% by 2050 compared to 2008. While liquified natural gas (LNG) has gained a strong foothold in the maritime sector over the past decades, the trend is shifting toward adopting lower and zero-carbon hydrogen and its carriers, such as methanol and ammonia, as alternative fuels. Quantifying risks from accidental leakages during storage and transfer of these alternative fuels using numerical models is required and commonly adopted in industries. The process leverages multiple models and tools for risk assessments with different accuracy levels and costs ranging from integral models to Lagrangian techniques and Eulerian approaches such as computational fluid dynamics (CFD). Increasingly, CFD approaches are employed for near-field dispersion analysis to assess the risk of accidental leakages. Despite their high computational cost, CFD models offer better accuracy than integral and Lagrangian models. In this work, we developed a CFD-based framework as a quantitative tool for risk assessment purposes. Our framework aims to (1) offer finer gas dispersion resolution with a detailed representation of surrounding structures and geometries, (2) minimize reliance on assumptions and empirical models to capture flow dynamics and gas dispersions accurately, and (3) mitigate conservative estimates and over-design of safety measures. The framework was validated using experimental data from various field tests, including a recent one involving releasing cryogenic liquids into the atmosphere. After successfully validating and comparing with experiments and other available tools, the proposed framework investigated gas plume dispersion from accidental leakages during fuel bunkering operations in ship-to-ship and shore-to-ship scenarios. The data obtained from CFD simulations was subsequently utilized to construct a surrogate model for fast prediction of gas plume behavior under varying environmental conditions. This facilitated the development of an effective emergency response plan.

SecureEI: Proactive intellectual property protection of AI models for edge intelligence

Deploying AI models on edge computing platforms enhances real-time performance, reduces network dependency, and ensures data privacy on terminal devices. However, these advantages come with increased risks of model leakage and misuse due to the vulnerability of edge environments to physical and cyber attacks compared to cloud-based solutions. To mitigate these risks, we propose SecureEI, a proactive intellectual property protection method for AI models that leverages model splitting and data poisoning techniques. SecureEI divides the model into two components: DeviceNet, which processes input data into protected license data, and EdgeNet, which operates on the license data to perform the intended tasks. This method ensures that only the transformed license data yields high model accuracy, while original data remains unrecognizable, even under fine-tuning attacks. We further employ targeted training strategies and weight adjustments to enhance the model’s resistance to potential attacks that aim to restore its recognition capabilities for original data. Evaluations on MNIST, Cifar10, and FaceScrub datasets demonstrate that SecureEI not only maintains high model accuracy on license data but also significantly bolsters defense against fine-tuning attacks, outperforming existing state-of-the-art techniques in safeguarding AI intellectual property on edge platforms.

Permeability evolution of sandstone caprock transverse fractures during intermittent CO2 injection in coal-bearing strata

The caprock of coal-bearing strata plays a critical role in CO2 geological storage, with the presence of fractures posing a heightened risk of CO2 leakage. The cyclic effects of CO2 injection and in situ stress influence the permeability of caprock fractures. However, the combined impact of CO2 and in situ stress on fracture permeability remains uncertain. This study conducted cyclic seepage experiments under varying amplitude stresses on fractured sandstone samples soaked in ScCO2 for different times (0, 15, 30, and 60 days). The microstructural characteristics of the fractured sandstone surfaces were analyzed using scanning electron microscopy and x-ray diffraction. The experimental results indicated that soaking in ScCO2 reduces sandstone fracture permeability, but the extent of this reduction is nonlinearly related to the soaking time. During the stress cycling process, due to the effect of plastic deformation, the permeability of sandstone fractures decreases with increasing cyclic amplitude and remains relatively constant with decreasing cyclic amplitude. At the same cyclic amplitude, the permeability of sandstone fractures initially increases and then decreases with prolonged soaking time. The impact of ScCO2 and stress cycling on the permeability of sandstone fractures is the result of a series of combined chemical–mechanical effects. The combined effects of chemical dissolution and mechanical degradation significantly influence the permeability of sandstone fractures, and this impact is notably time-dependent. During short-term soaking, geochemically induced changes in the surface structure of fractures cause fluctuations in permeability, while in long-term soaking, the combined chemical–mechanical effects promote a reduction in fracture permeability.

Optimizing CO2 Hydrate Sequestration in Subsea Sediments through Cold Seawater Pre-Injection

Carbon sequestration technology offers a solution to mitigate excessive carbon dioxide emissions and sustainable development in the future. This study proposes a method for subsea carbon sequestration through the injection of cold seawater to promote CO2 hydrate formation. Using a self-developed simulator, we modeled and calculated the long-term sequestration process. The study focuses on analyzing the thermal regulation of the seabed following cold seawater injection, the multiphysical field evolution during CO2 injection and long-term sequestration, and the impact of seawater injection volumes on sequestration outcomes. The feasibility and leakage risks of this method were evaluated on a 100,000-year timescale. Results indicate that the injection of cold seawater significantly improves the pressure–temperature conditions of subsea sediments, facilitating early hydrate formation and markedly increasing the initial CO2 hydrate formation rate. Consequently, the distribution pattern of hydrate saturation changes, forming a double-layer hydrate shell. Over the long term, while cold seawater injection does not significantly reduce CO2 leakage, it does increase the safety margin between the hydrate layer and the seabed, enhancing the safety coefficient for long-term CO2 hydrate sequestration. Through detailed analysis of the behavior of CO2 components during sequestration, this study provides new theoretical insights into subsea CO2 hydrate storage.

Vat photopolymerization for thermal energy storage applications using encapsulated phase change material suspended in photocurable resin

A novel approach to additively manufacture latent heat thermal energy storage heat exchangers through the development of microencapsulated phase change material (MEPCM) suspensions in photocurable resin for vat photopolymerization (VPP) 3D printing is presented. Using MEPCM addresses the leakage risks that have typically been associated with PCMs and subsequently makes the particulates a suitable additive for VPP 3D printing. In the current study, VPP was employed to fabricate functional composites with varying MEPCM mass fractions for thermal, rheological, microstructure, and chemical characterization. Microstructure visualization was conducted to assess the overall distribution of MEPCM within the 3D printed samples and to confirm the structural integrity of the encapsulated particles after printing. The influence of the base resin viscosity was explored by investigating two photocurable resins with different viscosities—a high-tensile UV photopolymer and an ABS-like resin—during the printing process. Thermal properties, such as latent heat of fusion, phase-change temperature, thermal conductivity, and decomposition temperature of the 3D printed samples were determined. Rheology was used to observe the effect of varying shear rates on the MEPCM-resin mixtures to identify the optimal viscoelastic properties for VPP 3D printing. It was determined that the ABS-like resin was able to contain a larger amount of PCM (40 wt%) while maintaining printability due to the lower viscosity of the corresponding pure resin. The 40 wt% MEPCM composite exhibited an average viscosity of 18,817 cPs, a maximum latent heat of fusion of 54.12 kJ/kg, and a 12.4 % reduction in thermal conductivity compared to the pure polymer.

Site characterization of the Endurance CO 2 store, Southern North Sea, UK

The Endurance saline aquifer CO 2 store in the UK North Sea is the planned storage site for CO 2 emissions that will be captured from the East Coast Cluster. The site has been characterized to assess its suitability for injectivity, containment and capacity. The injection target is the Early Triassic Bunter Sandstone Formation, consisting of fine-grained sandstones deposited in fluvial, lacustrine and playa lake environments that were subject to repeated aeolian and fluvial reworking. The sandstones have excellent reservoir quality and are likely to be well connected due to the lack of preserved heterolithic layers. The trap is a large, four-way dip-closed anticline, sealed by mudstones and evaporites of the Middle Triassic Dowsing Formation. The top seal sediments are laterally extensive and geomechanically strong, and faulting observed in the overburden does not appear to connect to the reservoir, providing confidence that CO 2 containment will be secure. The risk of leakage through existing legacy wells is assessed as low. The maximum effective CO 2 storage capacity is c . 450 Mt: Phase 1 development of 100 Mt is equivalent to a storage efficiency factor of 3%, which is achievable without the need for brine production. First injection is planned from 2027.

Impact of Clostridium difficile Infection Versus Colonization on Postoperative Outcomes After Oncological Colorectal Surgery: An Observational Single-Center Study With Propensity Score Analysis.

There is limited research available concerning the risk anastomotic leakage in the context of Clostridium difficile infection (CDI). Herein, we aim to elucidate the correlation between CDI, encompassing both preoperative asymptomatic C. difficile carriers (CDC) and postoperative hospital acquired C. difficile infections (HA-CDI), and the occurrence of anastomotic leakage in patients undergoing oncological colorectal surgery. This is an observational, single-center study. Data were sourced from surgical logs between 2018 and 2023, via the hospital's electronic system. Patients were split into three subgroups: CDC, HA-CDI, and control group (CG). Groups were compared in terms of patient characteristics, morbidity, and mortality via Fisher's exact test and Kruskal-Wallis test. One-to-one propensity score matching was performed to reduce selection bias. A total of 522 patients were analyzed, split into three subgroups: CDC, n = 35; HA-CDI, n = 27; CG, n = 460. One-to-one propensity score matching reduced the CG to 62 patients. Patients in the HA-CDI group had higher rates of overall morbidity (p < 0.0001), higher rates of anastomotic leaks (p = 0.002), more surgical site infections (SSI) (p = 0.001), and a longer length of stay (26 vs. 11.2 vs. 9.3 days, p < 0.001), while patients in the CDC group had comparable rates of complications with the CG. HA-CDI is associated with a higher risk of anastomotic leak after oncological colorectal surgery, while asymptomatic CDC do not have higher morbidity and may be operated electively, under standard CD treatment.

Privacy-Preserving Electric Vehicle Charging Recommendation by Incorporating Full Homomorphic Encryption and Secure Multi-Party Computing

Electric vehicle (EV) charging recommendation can significantly improve global planning performance, corresponding to an increasing risk of privacy leakage. Based on this, this paper investigates the privacy data preservation strategy during the interaction between EVs and charging facilities. It proposes a privacy preservation strategy that aims to ensure EV information security. In a cloud computing environment, users do not want other users and cloud providers to have access to their personal information, which is precisely the problem that secure multi-party computing (SMPC) can solve. At present, full homomorphic encryption (FHE) can solve the problem of user data privacy preservation in cloud computing and big data environments and can realize the whole encryption process. Therefore, a more reasonable charging station selection scheme is provided under the computation of privacy preservation strategies incorporating the FHE-SMPC method. The effectiveness and implementation feasibility of the designed privacy preservation strategy in practical applications is verified through testing and comparative analysis. The results show that the developed strategy can significantly reduce the risk of privacy leakage with limited communication resources and computation time consumption. The results provide new perspectives and methodologies for interactive privacy preservation between EVs and charging stations, with application potential.

An Exploration of College Students Online Privacy Protection Awareness and Behavior in the Social Media Era

Taking online privacy protection of college students in the social media era as an entry point, the study explored the current situation of college students use of social media platforms, their awareness and behavior of online privacy protection, as well as the influencing factors through questionnaire surveys and data analysis. The study found that most college students do not pay enough attention to online privacy protection, and there is a high risk of privacy leakage. Factors affecting college students awareness and behavior of online privacy protection include social media platform characteristics, personal factors, and social and cultural environments. In response to these problems, countermeasure suggestions such as strengthening the platform privacy protection function, enhancing college students privacy protection education, and improving self-protection awareness are put forward, with a view to providing reference for building a safe and harmonious online social environment.

Caprock sealing integrity and key indicators of CO2 geological storage considering the effect of hydraulic-mechanical coupling: X field in the Bohai Bay Basin, China

Caprock sealing efficiency is an essential guarantee for the long-term safety and stability of CO2 geological storage (CCS). However, the uncertainty in the physical and mechanical properties of deep formations poses challenges to accurately predict the risks of CO2 leakage resulting in CO2 breakthrough or caprock fracture. This study aims to address the issue of imperfect key indicators for caprock sealing by focusing on the CCS project in the Bohai Bay Basin, China. A hydraulic-mechanical (HM) coupling program without considering multiphase flow and the chemical reactions is secondary developed based on the finite element software ABAQUS. Furthermore, a three-dimensional finite element numerical model is established for the analysis of HM coupling, with pore pressure increment (∆PP), Coulomb failure stress (∆CFS) and displacement (U) as evaluation criteria. The Tornado analysis and response surface analysis are employed to analyze the impact of 17 indicators on the caprock sealing, including caprock thickness, burial depth, reservoir and caprock permeability parameters, and mechanical parameters. Subsequently, key performance indicators for caprock sealing are determined. The research results indicate that the reservoir permeability, injection rate, caprock permeability, caprock Young's modulus, caprock internal friction angle, caprock Poisson's ratio, and caprock burial depth are key indicators of caprock sealing capability. The reservoir permeability has a greater impact sensitivity compared to the caprock permeability. Pore pressure and displacement increase with increasing in reservoir permeability. The caprock's resistance to deformation and fracturing increases with increasing in Young's modulus and Poisson's ratio of caprock. This study provides valuable insights for evaluating caprock sealing during CO2 storage in saline aquifers.

Key Synchronization Method Based on Negative Databases and Physical Channel State Characteristics of Wireless Sensor Network.

Due to their inherent openness, wireless sensor networks (WSNs) are vulnerable to eavesdropping attacks. Addressing the issue of secure Internet Key Exchange (IKE) in the absence of reliable third parties like CA/PKI (Certificate Authority/Public Key Infrastructure) in WSNs, a novel key synchronization method named NDPCS-KS is proposed in the paper. Firstly, through an initial negotiation process, both ends of the main channels generate the same initial key seeds using the Channel State Information (CSI). Subsequently, negotiation keys and a negative database (NDB) are synchronously generated at the two ends based on the initial key seeds. Then, in a second-negotiation process, the NDB is employed to filter the negotiation keys to obtain the keys for encryption. NDPCS-KS reduced the risk of information leakage, since the keys are not directly transmitted over the network, and the eavesdroppers cannot acquire the initial key seeds because of the physical isolation of their eavesdropping channels and the main channels. Furthermore, due to the NP-hard problem of reversing the NDB, even if an attacker obtains the NDB, deducing the initial key seeds is computationally infeasible. Therefore, it becomes exceedingly difficult for attackers to generate legitimate encryption keys without the NDB or initial key seeds. Moreover, a lightweight anti-replay and identity verification mechanism is designed to deal with replay attacks or forgery attacks. Experimental results show that NDPCS-KS has less time overhead and stronger randomness in key generation compared with other methods, and it can effectively counter replay, forgery, and tampering attacks.

Comparative Evaluation of Microleakage in Endodontically Treated Teeth Using an Alkasite Restorative Material Versus Resin-Modified Glass Ionomer Cement (RMGIC) as an Intraorifice Barrier: A Study Protocol.

Background The most popular approach to treating pulpal and periapical disease is endodontic therapy, but the most common failure after root canal therapy, if not followed by planned rehabilitation of the tooth, is tooth fracture, which may be so severe in some cases needing extraction. Inadequate endodontic restorations increase the risk of fracture and coronal leakage, which can disseminate bacteria and their byproducts and perhaps lead to the failure of root canal therapy. In order to offer protection against masticatory forces along with compressive obturation forces that can lead to vertical root fracture, research has also supported the use of post-endodontic treatment restorative materials with an elastic modulus that is either greater or comparable to the tooth itself for post-endodontic restorations. Restorative materials that can bond to root dentin can be used to create intraorifice barriers, which prevent coronal microleakage and reinforce the radicular dentin. The current in vitro studyaims to assess the effects of various intraorifice barriers (an alkasite restorative material versus resin-modified glass ionomer cement) on the sealing ability of the intraorifice barriers following root canal therapy. Methodology In vitro, confocal laser microscopy is used to determine the microleakage of various intraorifice barriers. Conclusion The sealing ability of a post-endodontic restoration is crucial for the overall success of endodontic treatment, and this in vitro study protocol would ultimately help in selecting the appropriate intraorifice barrier.

Surgical and Endoscopic Approaches to Management of Submucosal Tumors of the Gastroesophageal Junction: Technical Considerations and Systematic Review of the Literature

Background: Gastroesophageal junction (GEJ) submucosal tumors are comprised predominantly of leiomyomas, followed by gastrointestinal stromal tumors. Methods: Herein we provide a comprehensive review of GEJ submucosal tumors including a systematic review of the literature. Results: Computed tomography, esophagogastroduodenoscopy, and endoscopic ultrasound are the most commonly used diagnostic imaging modalities. Surgical resection via laparoscopy is the most common treatment approach, with simultaneous upper endoscopy utilized in approximately half of the cases. Concomitant fundoplication is performed by certain groups to minimize risk for postoperative leak, gastroesophageal reflux, and esophagitis. Conclusions: Prospective studies evaluating long-term outcomes are needed to help guide treatment.

Research on the Construction of Scenarios for Blockchain to Empower Government Governance

This paper delves into the potential and practical challenges of blockchain in government governance. As a cutting-edge development in information and communication technology, blockchain offers unique capabilities in data management and value transfer, presenting new solutions for government governance. The article begins with an overview of the definition, connotation, and current application status of blockchain technology, and then constructs typical scenarios where blockchain technology empowers government governance, including electronic credentials, government data circulation, data resource sharing, collaborative office work, and digital rural revitalization. By realizing these scenarios, the paper analyzes the main problems and challenges faced by blockchain technology in government governance, such as inadequate infrastructure, data leakage risks, and difficulties in inter-departmental collaboration. Finally, a series of suggestions and prospects are put forward to promote the effective application of blockchain technology in digital government affairs, enhancing the transparency, efficiency, and intelligent level of government governance

Assessing the Impact of Hyperthermic Intraperitoneal Chemotherapy on Anastomotic Integrity after Cytoreductive Surgery in Gastrointestinal Malignancies

Peritoneal carcinomatosis (PC) from gastrointestinal malignancies, particularly colorectal and gastric cancers, represents a significant therapeutic challenge due to the diffuse nature of tumor spread. The combination of cytoreductive surgery (CRS) with hyperthermic intraperitoneal chemotherapy (HIPEC) has emerged as a promising treatment modality, offering potential survival benefits by targeting residual microscopic disease. However, this aggressive approach is associated with a heightened risk of gastrointestinal anastomotic leaks, one of the most severe complications of gastrointestinal surgery. These leaks result from a complex interplay of factors, including hyperthermia-induced ischemia, chemotherapy-induced cytotoxicity, and a pro-inflammatory cytokine cascade involving IL-6, TNF-α, and IL-1β, which impair tissue healing. Furthermore, dysbiosis of the intestinal microbiota induced by HIPEC contributes to local inflammation and an increased risk of infection, exacerbating the likelihood of anastomotic failure. The duration and temperature of the HIPEC procedure, the extent of surgery, and the patient’s performance status and tumor burden further influence the risk of leaks. Preventive strategies such as preoperative nutritional optimization, meticulous surgical technique, intraoperative reinforcement of anastomoses, and selective use of protective ileostomies are critical for minimizing these risks. Early detection and prompt management of leaks are essential for reducing morbidity and mortality, improving both short-term and long-term outcomes. This review comprehensively examines the multifactorial causes of anastomotic leaks in the setting of CRS and HIPEC and highlights potential strategies for prevention and improved management.

Modification of the lesser curvature incision line enhanced gastric conduit perfusion as determined by indocyanine green fluorescence imaging and decreased the incidence of anastomotic leakage following esophagectomy

Abstract Aim This study aimed to investigate the effectiveness of a modified incision line on the lesser curvature for gastric conduit formation during esophagectomy in enhancing the perfusion of gastric conduit as determined by indocyanine green fluorescence imaging and reducing the incidence of anastomotic leakage. Methods A total of 272 patients who underwent esophagectomy at our institute between 2014 and 2022 were enrolled in this study. These patients were divided based on two different types of cutlines on the lesser curvature: conventional group (n = 141) following the traditional cutline and modified group (n = 131) adopting a modified cutline. Gastric conduit perfusion was assessed by ICG fluorescence imaging, and clinical outcomes after esophagectomy were evaluated. Results The distance from the pylorus to the cutline was significantly longer in the modified group compared with the conventional group (median: 9.0 cm vs. 5.0 cm, p &lt; 0.001). The blood flow speed in the gastric conduit wall was significantly higher in the modified group than that in the conventional group (median: 2.81 cm/s vs. 2.54 cm/s, p = 0.001). Furthermore, anastomotic leakage was significantly lower (p = 0.024) and hospital stay was significantly shorter (p &lt; 0.001) in the modified group compared with the conventional group. Multivariate analysis identified blood flow speed in the gastric conduit wall as the only variable significantly associated with anastomotic leakage. Conclusions ICG fluorescence imaging is a feasible, reliable method for the assessment of gastric conduit perfusion. Modified lesser curvature cutline could enhance gastric conduit perfusion, promote blood circulation around the anastomotic site, and reduce the risk of anastomotic leakage after esophagectomy.

You Work for Us Now: Concentration in University-Performed Defense R&D

ABSTRACT Concentration in university research funded by the Department of Defense (DOD) has been rising in recent years, deviating from the steady levels of concentration in other federally-funded university research. The purpose of this paper is to explain that rise in concentration. When the DOD funds defense-specific R&D projects, there are two priorities affecting bureaucratic incentives: 1) Coordination incentivizes steering research toward specific technological ends, and 2) Security incentivizes actively limiting risks of information leakage. Sole source research center contracts make the necessary coordination and monitoring easier to achieve. As demand for projects that require more coordination and security increases, spending is allocated to sole source research centers leading to increasing concentration. Spending on military research projects awarded to universities such as aircrafts rapidly increased from 2008 to 2020 with much of that spending accruing to DOD-sponsored university research centers. Over that period, the share of obligations awarded to the 16 universities that manage DOD research centers rose from 37 percent in 2008 to 59 percent in 2020. This paper contributes to our understanding of the conditions under which policy makers choose to deviate from using grants to fund early-stage research and concentrate funding in a select group of performers.

A Privacy-Preserving Electromagnetic-Spectrum-Sharing Trading Scheme Based on ABE and Blockchain

The electromagnetic spectrum is a limited resource. With the widespread application of the electromagnetic spectrum in various fields, the contradiction between the demand for the electromagnetic spectrum and electromagnetic spectrum resources has become increasingly prominent. Spectrum sharing is an effective way to improve the utilization of the electromagnetic spectrum. However, there are many challenges in existing distributed electromagnetic spectrum trading based on blockchain technology. Since a blockchain does not provide privacy protection, the risk of privacy leakage during the trading process makes electromagnetic spectrum owners unwilling to share. In addition, a blockchain only guarantees integrity, and the imperfect trading dispute resolution mechanism causes electromagnetic spectrum owners to be afraid to share. Therefore, we propose a privacy-preserving electromagnetic-spectrum-sharing trading scheme based on blockchain and ABE. The scheme not only designs an ABE fine-grained access control model in ciphertext form but also constructs a re-encryption algorithm that supports trading arbitration to achieve privacy protection for electromagnetic spectrum trading. Finally, we experimentally evaluated the efficiency of the proposed electromagnetic spectrum trading scheme. The experimental results show that the electromagnetic spectrum trading scheme we propose was highly efficient.

Survey of federated learning in intrusion detection

Intrusion detection methods are crucial means to mitigate network security issues. However, the challenges posed by large-scale complex network environments include local information islands, regional privacy leaks, communication burdens, difficulties in handling heterogeneous data, and storage resource bottlenecks. Federated learning has the potential to address these challenges by leveraging widely distributed and heterogeneous data, achieving load balancing of storage and computing resources across multiple nodes, and reducing the risks of privacy leaks and bandwidth resource demands. This paper reviews the process of constructing federated learning based intrusion detection system from the perspective of intrusion detection. Specifically, it outlines six main aspects: application scenario analysis, federated learning methods, privacy and security protection, selection of classification models, data sources and client data distribution, and evaluation metrics, establishing them as key research content. Subsequently, six research topics are extracted based on these aspects. These topics include expanding application scenarios, enhancing aggregation algorithm, enhancing security, enhancing classification models, personalizing model and utilizing unlabeled data. Furthermore, the paper delves into research content related to each of these topics through in-depth investigation and analysis. Finally, the paper discusses the current challenges faced by research, and suggests promising directions for future exploration.

Integrating artificial intelligence into ERP systems: advantages, disadvantages and prospects

Objective: to identify the key benefits and potential risks associated with the use of artificial intelligence in ERP systems to improve decision-making processes, management efficiency and operational performance of various sectors, including commercial and non-profit organizations. Methods: systematic literature review, empirical data analysis, analytical and experimental research methods. Results: the key directions of artificial intelligence implementation in ERP-systems are reflected, providing improvement of operational efficiency, customer relations, as well as optimization of business processes, data management, supply chain and personnel management, automation of operations related to finance, optimization of customer relations; implementation of artificial intelligence in ERP-systems reduces inventory management costs, improves the accuracy of forecasting andinventory optimization, accelerates financial analysis and increases the accuracy of budgeting, resulting in reduced budget planning time; it also increases productivity by optimizing necessary production processes and reducing equipment downtime. However, there are also risks of confidential data leakage, unauthorized access to data; job losses due to automation of tasks; and vulnerability to cyberattacks. Scientific novelty: the little-studied directions of artificial intelligence integration in ERP-systems are analyzed; an integrative approach to the application of artificial intelligence in ERP-systems is proposed, which combines methods of machine learning, natural language processing and predictive analytics and provides a comprehensive assessment of the complex impact on the business processes’ efficiency. Practical significance: the formulated directions for solving the identified problems of artificial intelligence integration in ERP-systems can be implemented in practice, as they will enable to better take into account local requirements and laws.