Leveraging Dialogue State Tracking for Zero-Shot Chat-Based Social Engineering Attack Recognition

Abstract

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.

A Modular Framework for Domain-Specific Conversational Systems Powered by Never-Ending Learning

“…Future research efforts must consider other relevant nonfunctional aspects, such as availability, security, maintainability, and relevant trade-offs, possibly using the ATAM software engineering method [32]. As security is relevant for dialog systems [33], it could be interesting to consider a federated learning approach [34,35].…”

Cybercrime Intention Recognition: A Systematic Literature Review

“…Although these approaches do not require much domain knowledge or human intervention, they need a large amount of labeled data to train the models. Deep learning approaches are the current state of the art in the AI industry [14,[25][26][27][28][29][30][31][32][33][34]. They utilize deep neural networks to learn high-level features and representations from data, which can be used to recognize intents.…”

“…In this paper, we reviewed diverse criminal activities that have incorporated IR methodologies. While a substantial portion of the literature pertains to cyberincidents [16,18,20,31], there exist significant studies related to computer-facilitated offenses such as harassment [14,21,23,32,34], as well as crimes involving computers such as shoplifting [25,28,30,33]. In these scholarly works, IR techniques were instrumental during the collection [16,20,21], examination [16][17][18][19], and analysis [12,16,19,23] phases of DFI.…”

“…To add more to the chat-based social engineering (CSE) attack detection system, Tsinganos et al [34] propose a deep learning-based model for recognizing the intentions of CSE attacks using dialogue state tracking. They create an ontology and a small corpus called SG-CSE, and, adopted from BERT-base, they build a model called SG-CSE BERT.They test their model by using the dataset to evaluate their approach and achieve promising results.…”

Federated and Transfer Learning Applications

“…With this in mind, the present Special Issue of Applied Sciences on "Federated and Transfer Learning Applications" provides an overview of the latest developments in this field. Twenty-four papers were submitted to this Special Issue, and eleven papers [1][2][3][4][5][6][7][8][9][10][11] were accepted (i.e., a 45.8% acceptance rate). The presented papers explore innovative trends of federated learning approaches that enable technological breakthroughs in highimpact areas such as aggregation algorithms, effective training, cluster analysis, incentive mechanisms, influence study of unreliable participants and security/privacy issues, as well as innovative breakthroughs in transfer learning such as Arabic handwriting recognition, literature-based drug-drug interaction, anomaly detection, and chat-based social engineering attack recognition.…”