Social engineering is widely recognized as the key to successful cyber-attacks. Chat-based social engineering (CSE) attacks are attracting increasing attention because of recent changes in the digital work environment. Sophisticated CSE attacks target human personality traits, and persuasion is regarded as the catalyst to successful CSE attacks. To date, research in social engineering has mostly focused on phishing attacks, neglecting the importance of chat-based software. This paper describes the design and implementation of a persuasion classifier that utilizes machine learning and natural language processing techniques. For this purpose, a convolutional neural network was trained on a chat-based social engineering corpus (CSE Corpus), specifically annotated for recognizing Cialdini’s persuasion principles. The proposed persuasion classifier network, named CSE-PUC, can determine whether a sentence carries a persuasive payload by producing a probability distribution over the sentence classes as a persuasion container. The present study is expected to contribute to our understanding of utilizing existing machine learning models and integrating context-aware information into real-life cyber security threats. The experimental application results reported in this work confirm that the approach taken can recognize persuasion methods and is thus able to protect an interlocutor from being victimized.
Chat-based social engineering (CSE) attacks are attracting increasing attention in the Small-Medium Enterprise (SME) environment, given the ease and potential impact of such an attack. During a CSE attack, malicious users will repeatedly use linguistic tricks to eventually deceive their victims. Thus, to protect SME users, it would be beneficial to have a cyber-defense mechanism able to detect persistent interlocutors who repeatedly bring up critical topics that could lead to sensitive data exposure. We build a natural language processing model, called CSE-PersistenceBERT, for paraphrase detection to recognize persistency as a social engineering attacker’s behavior during a chat-based dialogue. The CSE-PersistenceBERT model consists of a pre-trained BERT model fine-tuned using our handcrafted CSE-Persistence corpus; a corpus appropriately annotated for the specific downstream task of paraphrase recognition. The model identifies the linguistic relationship between the sentences uttered during the dialogue and exposes the malicious intent of the attacker. The results are satisfactory and prove the efficiency of CSE-PersistenceBERT as a recognition mechanism of a social engineer’s persistent behavior during a CSE attack.
Human-to-human dialogues constitute an essential research area for linguists, serving as a conduit for knowledge transfer in the study of dialogue systems featuring human-to-machine interaction. Dialogue systems have garnered significant acclaim and rapid growth owing to their deployment in applications such as virtual assistants (e.g., Alexa, Siri, etc.) and chatbots. Novel modeling techniques are being developed to enhance natural language understanding, natural language generation, and dialogue-state tracking. In this study, we leverage the terminology and techniques of dialogue systems to model human-to-human dialogues within the context of chat-based social engineering (CSE) attacks. The ability to discern an interlocutor’s true intent is crucial for providing an effective real-time defense mechanism against CSE attacks. We introduce in-context dialogue acts that expose an interlocutor’s intent, as well as the requested information that she sought to convey, thereby facilitating real-time recognition of CSE attacks. Our work proposes CSE domain-specific dialogue acts, utilizing a carefully crafted ontology, and creates an annotated corpus using dialogue acts as classification labels. Furthermore, we propose SG-CSE BERT, a BERT-based model following the schema-guided paradigm, for zero-shot CSE attack dialogue-state tracking. Our evaluation results demonstrate satisfactory performance.
Chat-based Social Engineering (CSE) is widely recognized as a key factor to successful cyber-attacks, especially in small and medium-sized enterprise (SME) environments. Despite the interest in preventing CSE attacks, few studies have considered the specific features of the language used by the attackers. This work contributes to the area of early-stage automated CSE attack recognition by proposing an approach for building and annotating a specific-purpose corpus and presenting its application in the CSE domain. The resulting CSE corpus is then evaluated by training a bi-directional long short-term memory (bi-LSTM) neural network for the purpose of named entity recognition (NER). The results of this study emphasize the importance of adding a plethora of metadata to a dataset to provide critical in-context features and produce a corpus that broadens our understanding of the tactics used by social engineers. The outcomes can be applied to dedicated cyber-defence mechanisms utilized to protect SME employees using Electronic Medium Communication (EMC) software.
With the increasing prevalence of chat-based social engineering (CSE) attacks targeting unsuspecting users, the need for robust defenses has never been more critical. In this paper, we introduce Chat-based Social Engineering Attack Recognition System (CSE-ARS), an innovative and effective CSE defense system. CSE-ARS employs a late fusion strategy that integrates the findings of five specialized deep learning models, each focused on detecting distinct CSE attack enablers: critical information leakage recognizer (CRINL-R), personality traits recognizer (PERST-R), dialogue acts recognizer (DIACT-R), persuasion recognizer (PERSU-R), persistence recognizer (PERSI-R). The system harnesses weighted linear aggregation and employs simulated annealing with 10-fold cross-validation, ensuring optimal model performance. CSE-ARS is trained on the CSE-ARS Corpus, a carefully curated dataset tailored to the intricacies of CSE attacks. Extensive evaluation reveals that CSE-ARS achieves satisfactory results in identifying and neutralizing CSE threats, enhancing user security in online interactions.