Malware Research Articles

Detecting Malicious Twitter Bots using Machine Learning

Abstract: Twitter play a significant role in our daily lives, offering a wide range of opportunities to their users. However, Twitter and online social networks (OSNs) in general are increasingly being utilized by automated accounts, commonly known as bots, as they continue to gain immense popularity across various user demographics. Malicious twitter Bots detection is required to detect real users from fraudulent users because it leads to spreading of spam messages and engage in fraudulent activities. To overcome this, we are going to differentiate bots from legitimate users using feature extraction techniques and find malicious bots and tweets using machine learning algorithm and deep learning architecture known as VGG19 which is combined with the convolutional neural network (CNN) in order to identify whether the tweets are posted by bots or real users and also identifying malicious twitter bots along with malicious URLs. By following these techniques, we can identify the account as bots or real user and prevent spreading of malicious content in the society. The deep learning architecture combined with convolutional neural network to evaluate over a series of experiments using two large real Twitter datasets and compare the experimental results with other machine learning algorithms and provide advantages over other existing techniques like logistic regression targeting the identification of malicious users in social media.

HAVAE – An Advanced Approach for Malware Detection Using Deep Learning

Abstract: The dynamic situation of cybersecurity necessitates continuous adaptation to the evolving and sophisticated nature of malware. This study proposes an innovative approach to enhancing threat detection methodologies by combining Adversarial Autoencoders (AAEs) and Variational Autoencoders (VAEs) for unsupervised malware detection. AAEs, with their EncoderDecoder structure and adversarial techniques, are integrated with VAEs to discern latent representations which are crucial for discriminating between malware and harmless software. This model, referred to as Hybrid Adversarial-Variational Autoencoder (HAVAE), takes advantage of both of their strengths architectures, capturing nuanced features within a latent space through unsupervised learning. The HAVAE model employs the Reparameterization Technique, crucial for sampling latent variables, ensuring the generation of realistic samples while retaining discriminative attributes essential for accurate malware identification. Through comprehensive evaluations across diverse datasets, the efficiency of HAVAE is assessed using metrics encompassing precision, recall, and F1-score. The evaluation underscores the model's robust ability to detect malicious software effectively, emphasizing its potential as a versatile cybersecurity tool. This innovative approach represents a revolution in cybersecurity, utilizing the strength of unsupervised learning techniques, AAEs, and VAEs. The findings signify a significant advancement in adaptive and resilient malware detection systems, illuminating pathways for improved threat identification and mitigation in the ever-evolving cybersecurity landscape

Data correlation matrix-based spam URL detection using machine learning algorithms

In recent years, the widespread availability of internet access has brought both advantages and disadvantages. Users now enjoy numerous benefits, including unlimited access to vast amounts of information and seamless communication with others. However, this accessibility also exposes users to various threats, including malicious software and deceptive practices, leading to victimization of many individuals. Common issues encountered include spam emails, fake websites, and phishing attempts. Given the essential nature of internet usage in contemporary society, the development of systems to protect users from such malicious activities has become imperative. Accordingly, this study utilized eight prominent machine learning algorithms to identify spam URLs using a large dataset. Since the dataset only contained URL information and spam classification, additional feature extractions such as URL length and the number of digits were necessary. The inclusion of such features enhances decision-making processes within the framework of machine learning, resulting in more efficient detection. As the effectiveness of feature extraction significantly impacts the results of the methods, the study initially conducted feature extraction and trained models based on the weight of features. This paper proposes a data correlated matrix approach for spam URL detection using machine learning algorithms. The distinctive aspect of this study lies in the feature extraction process applied to the dataset, aimed at discerning the most impactful features, and subsequently training models while considering the weighting of these features. The entire dataset was used without any reduction in data. Experimental findings indicate that tree-based machine learning algorithms yield superior results. Among all applied methods, the Random Forest approach achieved the highest success rate, with a detection rate of 96.33% for the non-spam class. Additionally, a combined and weighted calculation method yielded an accuracy of 94.16% for both spam and non-spam data.

Enhanced Detection of Social Bots on Online Platforms using SemiSupervised K-Means Clustering

Social bots are semi-automatic or automatic computer applications that express human performance in OSN. Social bots are the primary tools utilized by hackers to invade OSNs. The current use of Social bots in communication and voting operations has been highlighted. Twitter and Tumblr have been efficiently used to share information about public sentiment. The developing connection on the Internet has started up avenues for improved cybersecurity threats and perpetuation of an extensive array of cybercrimes occurring in significant financial needs and user data privacy violations. One of the most advanced but critical extensions to the public of malicious software is the bot malware, commonly referred to as botnets. The most current presentation techniques of malicious social bots examine the quantitative characteristics of their behavior. This paper proposed a novel approach to identifying malicious social bots, including feature determination based on the development probability of clickstream progressions and the Semi-supervised K-Means Clustering algorithm for detecting social bots. The proposed method explains the transition probability of user behavior clickstreams and reflects the time feature. The proposed Semi-supervised K-Means Clustering (SSKMC) algorithm, compared with the traditional detection method based on the quantitative function, improves accuracy by 15% on average. The proposed SSKMC Algorithm can efficiently detect malicious accounts on social bots.

Towards a conceptual framework for ethical AI development in IT systems

The rapid advancement of artificial intelligence (AI) technologies has prompted significant societal, ethical, and legal concerns regarding their deployment in information technology (IT) systems. Addressing these concerns necessitates the establishment of a robust ethical framework to guide AI development and integration into IT systems. This paper presents a comprehensive conceptual framework aimed at fostering ethical AI development within IT systems. The proposed framework incorporates multidisciplinary perspectives, drawing upon principles from ethics, computer science, law, and philosophy. It emphasizes the integration of ethical considerations at every stage of the AI development lifecycle, including design, implementation, deployment, and maintenance. Central to this framework is the recognition of AI systems as socio-technical artifacts with profound impacts on individuals, communities, and societies at large. Key components of the framework include transparency, accountability, fairness, privacy, and security. Transparency entails ensuring that AI algorithms and decision-making processes are comprehensible and explainable to stakeholders, thereby fostering trust and enabling scrutiny. Accountability mechanisms are essential for attributing responsibility for AI-driven outcomes and facilitating recourse in cases of harm or injustice. Moreover, the framework emphasizes the importance of fairness in AI systems, advocating for the mitigation of biases and discrimination across diverse demographic groups. Privacy protection measures are deemed crucial to safeguarding individuals' personal data from unauthorized access or misuse, while robust security protocols are essential for defending against malicious exploitation and adversarial attacks. By delineating ethical guidelines and best practices, this conceptual framework aims to empower developers, policymakers, and organizations to navigate the complex ethical landscape of AI development in IT systems. Ultimately, the adoption of such a framework is imperative for harnessing the transformative potential of AI technologies while upholding fundamental ethical principles and societal values.

VORTEX : Visual phishing detectiOns aRe Through EXplanations

Phishing attacks reached a record high in 2022, as reported by the Anti-Phishing Work Group [1], following an upward trend accelerated during the pandemic. Attackers employ increasingly sophisticated tools in their attempts to deceive unaware users into divulging confidential information. Recently, the research community has turned to the utilization of screenshots of legitimate and malicious websites to identify the brands that attackers aim to impersonate. In the field of Computer Vision, convolutional neural networks (CNNs) have been employed to analyze the visual rendering of websites, addressing the problem of phishing detection. However, along with the development of these new models, arose the need to understand their inner workings and the rationale behind each prediction. Answering the question, “How is this website attempting to steal the identity of a well-known brand?” becomes crucial when protecting end-users from such threats. In cybersecurity, the application of explainable AI (XAI) is an emerging approach that aims to answer such questions. In this paper, we propose VORTEX, a phishing website detection solution equipped with the capability to explain how a screenshot attempts to impersonate a specific brand. We conduct an extensive analysis of XAI methods for the phishing detection problem and demonstrate that VORTEX provides meaningful explanations regarding the detection results. Additionally, we evaluate the robustness of our model against Adversarial Example attacks. We adapt these attacks to the VORTEX architecture and evaluate their efficacy across multiple models and datasets. Our results show that VORTEX achieves superior accuracy compared to previous models, and learns semantically meaningful patterns to provide actionable explanations about phishing websites. Finally, VORTEX demonstrates an acceptable level of robustness against adversarial example attacks.

HCNCT: A Cross-chain Interaction Scheme for the Blockchain-based Metaverse

As a new type of digital living space that blends virtual and reality, Metaverse combines many emerging technologies. It provides an immersive experience based on VR technology and stores and protects users’ digital content and digital assets through blockchain technology. However, different virtual environments are often highly heterogeneous in terms of underlying architecture and software implementation technology, which leads to many challenges in scalability and interoperability for blockchains serving the Metaverse. Cross-chain technology is an essential technology to realize the scalability and interoperability of blockchain. However, the current cross-chain technologies all have their own merits and demerits, and there is no cross-chain solution that can be fully applied to any scenario. To this end, in the blockchain-based Metaverse, this article proposes a cross-chain transaction scheme based on improved hash timelock, HCNCT. By combining the notary mechanism, this scheme uses a group of notaries to supervise and participate in cross-chain transactions, effectively solving the problem that malicious users create a large number of time-out transactions to block the transaction channel, which exists in the traditional hash timelock method. Besides, this article uses the verifiable secret sharing method in the notary group, which can effectively prevent the centralization problem of the notary mechanism. Moreover, this article discusses the process of key processing, cross-chain transaction and transaction verification of the scheme, and designs the user credibility evaluation mechanism, which can effectively reduce the occurrence of malicious default of users. Compared with existing solutions, our solution has the advantage of effectively addressing time-out transaction attacks and centralization issues while guaranteeing security. The experiments also verify the effectiveness of the proposed scheme.

Rumor Detection with A Novel Graph Neural Network Approach

The wide spread of rumors[3] on social media has caused a negative impact on people's daily life, leading to potential panic, fear and mental health problems for the public.[47] How to debunk rumors as early as possible remains a challenging problem. Existing studies mainly leverage information propagation structure to detect rumors[6], while very few works focus on correlation among users that they may coordinate to spread rumors in order to gain a large popularity. In this paper, we propose a new detection model, that jointly learns both the representations of user correlation and information propagation to detect rumors on social media. Specifically, we leverage graph neural networks to learn the representations of user correlation from a bipartite graph[5] that describes the correlations between users and source tweets[12], and the representations of information propagation with a tree structure. Then we combine the learned representations from these two modules to classify the rumors. Since malicious users intend to subvert our model after deployment, we further develop a greedy attack scheme to analyze the cost of three adversarial attacks: graph attack, comment attack and joint attack. Evaluation results on two public datasets illustrate that the proposed MODEL outperforms the state-of-the-art rumor detection models. We also demonstrate our method performs well for early rumor detection.[8] Moreover, the proposed detection method is more robust to adversarial attacks compared to the best existing method. Importantly, we show that it requires high cost for attackers to subvert user correlation pattern, demonstrating the importance of considering user correlation for rumor detection.

Malicious Packet Detection Technology Using Reinforcement Learning

In the present day, the advancement of 5G and Internet of Things (IoT) technology has resulted in the interconnectedness of everyday objects through networks. However, attempts to exploit networked computers for malicious purposes continue to rise while the attacks utilizing malicious codes to compromise user information's confidentiality and integrity are becoming increasingly sophisticated and intelligent. To counter these evolving threats, researches have been conducted on a method to identify malicious network packets using a combination of security control systems and Artificial Intelligence (AI) technology, especially supervised learning. Unfortunately, the current cybersecurity control systems suffer from inefficiencies in terms of both manpower and cost. Moreover, the surge in remote work has created challenges in responding swiftly to security incidents. Furthermore, the existing AI technology based on supervised learning has limitations, particularly in detecting new variants of malicious code, and its accuracy in identifying malicious code depends heavily on the quantity and quality of available data. In light of these challenges, this study, reinforcement learning is employed to overcome the limitations of the original supervised learning-based malicious packet detection system, such as high dependency on training data and the failure to detect variant malicious packets. This research proposes a malicious packet detection technology capable of addressing new malicious packets or variant types effectively.

Detection of anomalous ticket purchasing behavior for concerts based on machine learning

In recent years, there has been a continuous increase in the demand for entertainment activities. With the changing policies related to epidemic prevention and control, consumers ticket demands for various entertainment events, particularly concerts, have seen a significant rise. This has led to the emergence of anomalous ticket purchasing behaviors, including ticket scalping software, bulk purchasing, and fraudulent transactions. Such behaviors not only infringe upon the rights of legitimate audiences but also harm the interests of concert organizers. Therefore, the detection and prevention of anomalous ticket purchasing behaviors for concerts have become essential. This paper focuses on the use of automated systems, robots, or malicious software for ticket purchases, limiting consumers participation in abnormal ticket-buying activities. Combining previous research on railway ticketing systems and real-life experiences, this study selects ticket-purchasing frequency, speed, quantity, seat selection, payment method, IP address changes, and historical ticket-purchasing records as feature values. Different machine learning models are chosen for different feature values to conceptualize the construction of an anomalous ticket purchasing system for concerts. This paper emphasizes the importance of detecting anomalous concert ticket purchasing behavior, provides different machine learning models for various feature values, and lays the foundation for building an overall anomaly detection system. This research serves as a crucial reference for the security and user experience of ticketing systems, aiming to continually improve and upgrade anomaly detection systems to adapt to evolving challenges. The hope is to enhance the ticket-buying experience for future concerts and large-scale events.

OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples

Large Language Models (LLMs) have achieved human-level fluency in text generation, making it difficult to distinguish between human-written and LLM-generated texts. This poses a growing risk of misuse of LLMs and demands the development of detectors to identify LLM-generated texts. However, existing detectors lack robustness against attacks: they degrade detection accuracy by simply paraphrasing LLM-generated texts. Furthermore, a malicious user might attempt to deliberately evade the detectors based on detection results, but this has not been assumed in previous studies. In this paper, we propose OUTFOX, a framework that improves the robustness of LLM-generated-text detectors by allowing both the detector and the attacker to consider each other's output. In this framework, the attacker uses the detector's prediction labels as examples for in-context learning and adversarially generates essays that are harder to detect, while the detector uses the adversarially generated essays as examples for in-context learning to learn to detect essays from a strong attacker. Experiments in the domain of student essays show that the proposed detector improves the detection performance on the attacker-generated texts by up to +41.3 points F1-score. Furthermore, the proposed detector shows a state-of-the-art detection performance: up to 96.9 points F1-score, beating existing detectors on non-attacked texts. Finally, the proposed attacker drastically degrades the performance of detectors by up to -57.0 points F1-score, massively outperforming the baseline paraphrasing method for evading detection.

RRL: Recommendation Reverse Learning

As societies become increasingly aware of data privacy, regulations require that private information about users must be removed from both database and ML models, which is more colloquially called `the right to be forgotten`. Such privacy problems of recommendation systems, which hold large amounts of private data, are drawing increasing attention. Recent research suggests dividing the preference data into multiple shards and training submodels with these shards and forgetting users' personal preference data by retraining the submodels of marked shards. Despite the computational efficiency development compared with retraining from scratch, the overall recommendation performance deteriorates after dividing the shards because the collaborative information contained in the training data is broken. In this paper, we aim to propose a forgetting framework for recommendation models that neither separate the training data nor jeopardizes the recommendation performance, named Recommendation Reverse Learning (RRL). Given the trained recommendation model and marked preference data, we devise Reverse BPR Objective (RBPR Objective) to fine-tune the recommendation model to force it to forget the marked data. Nevertheless, as the recommendation model encode the complex collaborative information among users, we propose to utilize Fisher Information Matrix (FIM) to estimate the influence of reverse learning on other users' collaborative information and guide the updates of representations. We conduct experiments on two representative recommendation models and three public benchmark datasets to verify the efficiency of RRL. To verify the forgetting completeness, we use RRL to make the recommendation model poisoned by shilling attacks forget malicious users.

Secrecy Enhancement of relay cooperative NOMA network based on user behavior

From the perspective of information security, relays exhibit varying levels of trustworthiness when forwarding information. For screening and eliminating the malicious users of cooperative NOMA relay networks, a reputation-based algorithm is proposed, in which the user relays (URs) are categorized into three types based on their behaviors—malicious users, speculative users, and honest users. Meanwhile, in order to minimize information leakage at the relay, cooperative interference signals are transmitted by far user (FU) and near user (NU) via the uplink while the base station (BS) is also transmitting signals to the relay. This approach increases inter-user interference (IUI) to confuse the eavesdropping capability of the relay. To verify the superiority of the proposed scheme, an asymptotic lower bound expression for the ergodic secrecy rate (ESR) of the downlink is derived to characterize the secrecy performance of the proposed scheme. Furthermore, in the case of limited system power, a joint power allocation algorithm based on the golden section method is also proposed to further enhance the security performances of the system. The simulation results validate the accuracy of the derived analysis results and demonstrate that the proposed scheme has a significant improvement in the ESR compared with the traditional scheme.

On the Impact of CDL and TDL Augmentation for RF Fingerprinting Under Impaired Channels

Cyber-physical systems have recently been used in several areas (such as connected and autonomous vehicles) due to their high maneuverability. On the other hand, they are susceptible to cyber-attacks. Radio frequency (RF) fingerprinting emerges as a promising approach. This work aims to analyze the impact of decoupling tapped delay line and clustered delay line (TDL+CDL) augmentation-driven deep learning (DL) on transmitter-specific fingerprints to discriminate malicious users from legitimate ones. This work also considers 5G-only-CDL, WiFi-only-TDL augmentation approaches. RF fingerprinting models are sensitive to changing channels and environmental conditions. For this reason, they should be considered during the deployment of a DL model. Data acquisition can be another option. Nonetheless, gathering samples under various conditions for a train set formation may be quite hard. Consequently, data acquisition may not be feasible. This work uses a dataset that includes 5G, 4G, and WiFi samples, and it empowers a CDL+TDL based augmentation technique in order to boost the learning performance of the DL model. Numerical results show that CDL+TDL, 5G-only-CDL, and WiFi-only-TDL augmentation approaches achieve 87.59%, 81.63%, 79.21% accuracy on unobserved data while TDL/CDL augmentation technique and no augmentation approach result in 77.81% and 74.84% accuracy on unobserved data, respectively.

FedMUP: Federated learning driven malicious user prediction model for secure data distribution in cloud environments

Cloud computing is flourishing at a rapid pace. Significant consequences related to data security appear as a malicious user may get unauthorized access to sensitive data which may be misused, further. This raises an alarm-ringing situation to tackle the crucial issue related to data security and proactive malicious user prediction. This article proposes a Federated learning driven Malicious User Prediction Model for Secure Data Distribution in Cloud Environments (FedMUP). This approach firstly analyzes user behavior to acquire multiple security risk parameters. Afterward, it employs the federated learning-driven malicious user prediction approach to reveal doubtful users, proactively. FedMUP trains the local model on their local dataset and transfers computed values rather than actual raw data to obtain an updated global model based on averaging various local versions. This updated model is shared repeatedly at regular intervals with the user for retraining to acquire a better, and more efficient model capable of predicting malicious users more precisely. Extensive experimental work and comparison of the proposed model with state-of-the-art approaches demonstrate the efficiency of the proposed work. Significant improvement is observed in the key performance indicators such as malicious user prediction accuracy, precision, recall, and f1-score up to 14.32%, 17.88%, 14.32%, and 18.35%, respectively.

Monitoring and Management of Phishing and Malicious Websites using Machine Learning

- Phishing internet sites are one of the internet protections issues that focus on human vulnerabilities rather than software program vulnerabilities. It can be defined because of the process of attracting online users to gain their touchy facts which include usernames and passwords. In this paper, we provide a sensible machine for detecting phishing websites. The gadget acts as a further functionality to an internet browser as an extension that routinely notifies the consumer whilst it detects a phishing internet site. The system is based on a device gaining knowledge of approach, particularly supervised mastering. We have decided on the XGBoost method because of its true overall performance in classification. Our focus is to pursue a better overall performance classifier by analyzing the features of phishing websites and choose the better aggregate of them to train the classifier. As a result, we finished our paper with accuracy of 99% accuracy with 48 features.

MADRAS-NET: A deep learning approach for detecting and classifying android malware using Linknet

Malware is an intentionally created malicious software that still poses a serious threat in cyberspace. Android malware has become one of the most significant online threats in recent years due to its increase in prevalence. Even though a lot of work has gone into identifying and categorizing Android malware, problems including data theft, difficulties identifying Android malware, and time-consuming detection remain unresolved. To overcome this issue, this paper proposed a Deep Learning (DL) Based Malware Attack DetectoR in Android Smartphones using LinkNET (MADRAS-NET) which effectively detects and mitigates the types of malwares in Android devices. The Max Abs Scaler receives a set of data as input first for pre-processing. Following pre-processing, the output is sent to LinkNET for classification. LinkNET uses the pre-processed data to identify malware, and then divides the output into three groups: real users, Penetho malware, and FakeAV malware. Lastly, the AndMal2020 dataset, which detects and classifies malware as well as malware families, is used to evaluate the suggested MADRAS-NET approach. The suggested LinkNET achieves a maximum accuracy of 99.81%, while other models, such as the Deep Belief Network (DBN) at 96.75%, the Generative Adversarial Network (GAN) at 94.42%, and the Long Short Term Memory Network (LSTM) at 93.11%, achieve similar results. The comparison of the MADRAS-NET model with the LSTM, GAN, and DBN frameworks indicates its better performance.

The power of generative AI in cybersecurity: Opportunities and challenges

This paper undertakes a comprehensive exploration of the potential and challenges presented by Generative Artificial Intelligence, with particular emphasis on the GPT models, in the field of cybersecurity. Through a meticulous examination of existing literature and pertinent case studies, the paper evaluates the capabilities of these models in the detection and rectification of vulnerabilities, as well as in identifying malicious code. It also highlights the pivotal role of generative AI in enhancing honeypot technology, which has shown promising results in proactive threat detection. While underscoring the significant advantages of utilizing generative AI in bolstering cybersecurity measures, the paper does not shy away from shedding light on the accompanying security exposures. These range from traditional threats like vulnerabilities and privacy breaches to novel dangers such as jailbreaking, prompt injection, and prompt leakage that are associated with the deployment of these AI models. The overarching objective of this paper is to contribute to the ongoing dialogue about the integration of advanced AI technologies into cybersecurity strategies while emphasizing the importance of vigilance against potential misuse. The paper concludes with a call for continued research and development to ensure a safer and more secure cyberspace for all.

TOWARDS A CONCEPTUAL FRAMEWORK FOR ETHICAL AI DEVELOPMENT IN IT SYSTEMS

The rapid advancement of artificial intelligence (AI) technologies has prompted significant societal, ethical, and legal concerns regarding their deployment in information technology (IT) systems. Addressing these concerns necessitates the establishment of a robust ethical framework to guide AI development and integration into IT systems. This paper presents a comprehensive conceptual framework aimed at fostering ethical AI development within IT systems. The proposed framework incorporates multidisciplinary perspectives, drawing upon principles from ethics, computer science, law, and philosophy. It emphasizes the integration of ethical considerations at every stage of the AI development lifecycle, including design, implementation, deployment, and maintenance. Central to this framework is the recognition of AI systems as socio-technical artifacts with profound impacts on individuals, communities, and societies at large. Key components of the framework include transparency, accountability, fairness, privacy, and security. Transparency entails ensuring that AI algorithms and decision-making processes are comprehensible and explainable to stakeholders, thereby fostering trust and enabling scrutiny. Accountability mechanisms are essential for attributing responsibility for AI-driven outcomes and facilitating recourse in cases of harm or injustice. Moreover, the framework emphasizes the importance of fairness in AI systems, advocating for the mitigation of biases and discrimination across diverse demographic groups. Privacy protection measures are deemed crucial to safeguarding individuals' personal data from unauthorized access or misuse, while robust security protocols are essential for defending against malicious exploitation and adversarial attacks. By delineating ethical guidelines and best practices, this conceptual framework aims to empower developers, policymakers, and organizations to navigate the complex ethical landscape of AI development in IT systems. Ultimately, the adoption of such a framework is imperative for harnessing the transformative potential of AI technologies while upholding fundamental ethical principles and societal values.
 Keywords: Ethical, AI, IT, System, Framework, Development, Review.

Uncovering the authorship: Linking media content to social user profiles

The extensive spread of fake news on social networks is carried out by a diverse range of users, encompassing private individuals, newspapers, and organizations. With widely accessible image and video editing tools, malicious users can easily create manipulated media. They can then distribute this content through multiple fake profiles, aiming to maximize its social impact. To tackle this problem effectively, it is crucial to possess the ability to analyze shared media to identify the originators of fake news. To this end, multimedia forensics research has advanced tools that examine traces in media, revealing valuable insights into its origins. While combining these tools has proven to be highly efficient in creating profiles of image and video creators, it is important to note that most of these tools are not specifically designed to function effectively in the complex environment of content exchange on social networks. In this paper, we introduce the problem of establishing associations between images and their source profiles as a means to tackle the spread of disinformation on social platforms. To this end, we assembled SocialNews, an extensive image dataset comprising more than 12,000 images sourced from 21 user profiles across Facebook, Instagram, and Twitter, and we propose three increasingly realistic and challenging experimental scenarios. We present two simple yet effective techniques as benchmarks, one based on statistical analysis of Discrete Cosine Transform (DCT) coefficients and one employing a neural network model based on ResNet, and we compare their performance against the state of the art. Experimental results show that the proposed approaches exhibit superior performance in accurately classifying the originating user profiles.