- Research Article
- 10.2139/ssrn.3733991
Ethics for Lawyers in the Cyber World
- Dec 02, 2020
- SSRN Electronic Journal
- Herrick K Lidstone
Ethics for Lawyers in the Cyber World
Recently, cyber security events have been gathered as a kind of Cyber Threat Intelligence(CTI) to fight against cyber attacks. Developing a cyber events analysis model to predict the possible threats can assist organizations in providing guidance for decision making. A cyber security event is a complete semantic unit containing all the participating objects (such as attacks assets and organizations) with rich attributes (such as the results and variety of the attack). However, existing cyber security events modeling works ignore the attributes of the objects and analyze the objects' relationships independently. To predict the possible threats for the organizations, we propose a cyber events embedding framework CyEvent2vec to model cyber security events with attributes. First, to effectively depict the cyber security events with attributes that happened in organizations, cyber security events are reconstructed by the organization and processed into the events matrices. Second, to explore the intricate relationships between heterogeneous objects in events, the events matrices are fed into the autoencoder model to get the low-dimensional embeddings. Third, to predict the possible threats for the victim organization, we apply the embeddings to two applications to measure the relevance between the objects: organization threats prediction and threat objects classification. Experiments show CyEvent2vec outperforms the other six representation learning methods on three real-world datasets.
Ethics for Lawyers in the Cyber World
Ethics for Lawyers in the Cyber World
Towards end-to-end Cyberthreat Detection from Twitter using Multi-Task Learning
Continuously striving for cyberthreat awareness is an essential task to secure an IT infrastructure. Analysts must guarantee access to information on the most up-to-date cybersecurity events and threats. This monitoring process is often the job of a security information and event management system, which relies on the timeliness and relevance of its feeds. There has been growing interest in exploiting open source intelligence for this purpose, mainly due to its timeliness and volume. Social media sites such as Twitter, are capable of aggregating numerous cybersecurity-related sources and act as a stream of information that can be used to feed a cyberthreat intelligence platform. In this paper, we present a multi-task learning approach combining two Natural Language Processing tasks for cyberthreat intelligence. Our pipeline is capable of reading a stream of tweets from a set of Twitter accounts and, through a shared deep neural network architecture, simultaneously identify relevant cybersecurity-related content and extract indicators of compromise therein. We show that in comparison to the traditional independent tasks baseline, one of the tasks achieves a slight F1 score improvement, while the other task is able to maintain its performance. Thus, the proposed approach greatly simplifies the pipeline and the requirements for data and online model adaptation over time, without sacrificing functional performance.
Read moreIoCMiner: Automatic Extraction of Indicators of Compromise from Twitter
In recent years, cyber attacks have consistently grown in terms of volume, sophistication, coordination, and pervasiveness. Such attacks impose billions of dollars loss to companies and government entities annually. Sharing cyber threat intelligence (CTI) about ongoing attacks can significantly improve the current situation as many cyber attackers tend to reuse or share their network infrastructure, techniques, tactics, and procedures across multiple attacks. Therefore, many security professionals devote their time and effort on hunting cyber threats and sharing such valuable information with the public through public data sharing platforms such as social media and text sharing websites. However, due to the sheer volume of information that is being shared on such platforms; finding CTI information is tantamount to looking for a needle in a haystack. In this paper, we present a new scalable framework, IoCMiner, to automatically extract CTI, in special Indicators of Compromise, from Twitter. It utilizes a combination of graph theory, machine learning, and text mining technique to achieve its goal. IoCMiner relies on a reputation model to discover credible twitterers who publish CTI, and only tracks the tweet stream of such Twitter handles. Moreover, it employs a CTI classifier to further filter out non-CTI tweets from the observed data streams. Finally, IoCs uses a set of regular expression rules to extract IoCs from the identifies tweets. Through experimentation, we show the usefulness of IoCMiner in finding fresh IoCs from Twitter. In the course of four weeks, IoCMiner identified more than 1,200 IoCs, including malicious URLs. Only 10% of the URLs were already listed in public blacklist databases at the time of extraction. The number of URLs that appeared in blacklists increased to 26% after one week.
Read moreOTX AlienVault Indicator of Compromise Implementation on MISP Threat Sharing for Network Intrusion Detection System Suricata
In the ever-evolving cyber era, cyberattack threats are increasingly diverse and elusive. Precise and complete information related to cyber attacks can be utilised to create a reliable network security system that is able to adapt automatically, so that the network is better protected from future threats. Based on the Security Landscape of the National Cyber and Crypto Agency in 2023 there are <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$403,990,813$</tex> anomaly traffic which are considered cyber attacks. From the data above, an early detection system is needed using a Network Intrusion Detection System (NIDS) that always updates its rules to monitor network traffic. Information from Cyber Threat Intelligence (CTI) results is needed to update NIDS rules. CTI is analysed and relevant information about cyber threats that can be used to understand cyber attacks. The form of CTI results is Indicator of Compromise which contains a list of valid attack attributes. This research implements the AlienVault OTX Indicator of Compromise in MISP Threat Sharing to provide automatic rules updates and improve the performance of Suricata NIDS, Suricata is a NIDS with high detection accuracy because it applies several detection engines or multi-threading. The experimental results show that before the rules update, Suricata was unable to detect the tested attack scenarios, whereas after applying the updated rules from MISP Threat Sharing, Suricata successfully detected 100% of the three attack scenarios. In addition, the average processing time recorded was 347 seconds for fetching IoCs from OTX to MISP and 84 seconds for exporting rules from MISP to Suricata, indicating that the update mechanism can be executed efficiently.
Read moreCyber Threat Intelligence – What Does It Even Mean?
In the simplest possible terms, cyber threat intelligence (CTI) is the process of taking disparate pieces of information about a cyber attack and identifying the context in which it happened and what that means. It is the same process a traditional intelligence analyst working for the military or law enforcement would apply to an investigation; it just sits within the realms of cybersecurity.
Read moreCyber Threat Intelligence: Current Trends and Future Perspectives
Many organizations are continually put in danger by sophisticated and malevolent cyber attacks in today's rapidly developing threat landscape, which is evolving at a rapid rate. Cybercriminals, who are more skilled, more organized, and have more financial resources than in the past. Cyber Threat Intelligence, abbreviated as CTI, has emerged as a popular topic and is now being considered by many organizations as a potential solution to the growing number of cyber attacks. The purpose of this work is to conduct a literature review on the previous research that has been done on CTI. The most fundamental question about what CTI is investigated through the process of doing a literature study. This is done by contrasting several definitions in order to identify areas of agreement and disagreement. It has been discovered that neither the organization nor the suppliers have a comprehensive grasp of the information that is deemed to be CTI; hence, further study is required in order to define CTI. This article also listed existing CTI products and services, including as threat intelligence data feeds, threat intelligence standards, and tools that are being utilized in CTI. This study outlines four research issues in cyber threat intelligence and assesses contemporary work carried out in each of those areas. These difficulties were determined based on an assessment of the CTI definition, standards, and technologies. When an organization is inundated with a massive amount of threat data, the need for trained threat data analysts who are able to fully utilize CTI and transform the data into actionable information becomes more vital than it has ever been before. The problem of poor data quality is not a recent development; nonetheless, because to the increasing use of CTI, further study in this field is required.
Read moreCyber Threat Intelligence for Improving Cyber Supply Chain Security
Cyber supply chain (CSC) systems provide operational efficiency and business continuity due to the integrated nature of various network system nodes. Such integration has made the overall system vulnerable to various cyber attacks and malware propagation is one of the common attacks for CSC. Cyber threat intelligence (CTI) provides an organization the capability to identify, gather, analyze threats and the associated risks so that CSC organization can forecast the existing and future threat trends and manage the cybersecurity risk in a proactive manner. A threat actor may attack the system and propagate a malware. The purpose is to manipulate, alter, or change delivery mechanisms. It is imperative to integrate CTI into the existing cybersecurity practice to detect and understand the threat actor's intents and motive. In our previous paper, we used threat analysis gathering to provide us an understanding of the adversaries' capabilities, actions, and intents. This paper contributes to improving the cybersecurity of CSC by using CTI. In particular, we extend our previous work which identifies and analysis CSC attacks and adopts CTI approach to understand the attack trends so that appropriate control can determine proactively. We use the malware a smart grid case study as CSC context to demonstrate our approach. The result demonstrations how CTI approach is applied to assist in preventing cyberattacks and to disseminate threat information sharing.
Read moreAttack Behavior Extraction Based on Heterogeneous Cyberthreat Intelligence and Graph Convolutional Networks
The continuous improvement of the cyber threat intelligence sharing mechanism provides new ideas to deal with Advanced Persistent Threats (APT). Extracting attack behaviors, i.e., Tactics, Techniques, Procedures (TTP) from Cyber Threat Intelligence (CTI) can facilitate APT actors’ profiling for an immediate response. However, it is difficult for traditional manual methods to analyze attack behaviors from cyber threat intelligence due to its heterogeneous nature. Based on the Adversarial Tactics, Techniques and Common Knowledge (ATT&CK) of threat behavior description, this paper proposes a threat behavioral knowledge extraction framework that integrates Heterogeneous Text Network (HTN) and Graph Convolutional Network (GCN) to solve this issue. It leverages the hierarchical correlation relationships of attack techniques and tactics in the ATT&CK to construct a text network of heterogeneous cyber threat intelligence. With the help of the Bidirectional Encoder Representation from Transformers (BERT) pretraining model to analyze the contextual semantics of cyber threat intelligence, the task of threat behavior identification is transformed into a text classification task, which automatically extracts attack behavior in CTI, then identifies the malware and advanced threat actors. The experimental results show that F1 achieve 94.86% and 92.15% for the multi-label classification tasks of tactics and techniques. Extend the experiment to verify the method’s effectiveness in identifying the malware and threat actors in APT attacks. The F1 for malware and advanced threat actors identification task reached 98.45% and 99.48%, which are better than the benchmark model in the experiment and achieve state of the art. The model can effectively model threat intelligence text data and acquire knowledge and experience migration by correlating implied features with a priori knowledge to compensate for insufficient sample data and improve the classification performance and recognition ability of threat behavior in text.
Read moreAPT-scope: A novel framework to predict advanced persistent threat groups from enriched heterogeneous information network of cyber threat intelligence
APT-scope: A novel framework to predict advanced persistent threat groups from enriched heterogeneous information network of cyber threat intelligence
Read moreBFLS: Blockchain and Federated Learning for sharing threat detection models as Cyber Threat Intelligence
BFLS: Blockchain and Federated Learning for sharing threat detection models as Cyber Threat Intelligence
Learning optimal heterogeneous service network representation
In this paper, we propose an approach to learn optimal service representations that can be used in downstream data mining tasks by combining attributes and multiple relations from a heterogeneous information network and using meta-paths to model service relations. We construct a heterogeneous information network that connects services, mashups, and their attributes and derive latent relational knowledge from it for representation learning. We address two major challenges related to using such a heterogeneous network in representation learning: (1) how to effectively combine attribute information and network topology, (2) how to optimize the weighting scheme among those inputs to enhance the learning from relevant features and minimize distraction from noisy ones. Our approach can take advantage of partially or fully annotated data, and still works in a fully unsupervised setting. We conduct a comprehensive experimental study on a real world dataset, where we use clustering as a downstream task. In our experiments, Our model performs better than all competing approaches.
Read moreQuery-dependent cross-domain ranking in heterogeneous network
Traditional learning-to-rank problem mainly focuses on one single type of objects. However, with the rapid growth of the Web 2.0, ranking over multiple interrelated and heterogeneous objects becomes a common situation, e.g., the heterogeneous academic network. In this scenario, one may have much training data for some type of objects (e.g. conferences) while only very few for the interested types of objects (e.g. authors). Thus, the two important questions are: (1) Given a networked data set, how could one borrow supervision from other types of objects in order to build an accurate ranking model for the interested objects with insufficient supervision? (2) If there are links between different objects, how can we exploit their relationships for improved ranking performance? In this work, we first propose a regularized framework called HCDRank to simultaneously minimize two loss functions related to these two domains. Then, we extend the approach by exploiting the link information between heterogeneous objects. We conduct a theoretical analysis to the proposed approach and derive its generalization bound to demonstrate how the two related domains could help each other in learning ranking functions. Experimental results on three different genres of data sets demonstrate the effectiveness of the proposed approaches.
Read moreConstrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation
Fairness-aware recommendation eliminates discrimination issues to build trustworthy recommendation systems. Existing fairness-aware approaches ignore accounting for rich user and item attributes and thus cannot capture the impact of attributes on affecting recommendation fairness. These real-world attributes severely cause unfair recommendations by favoring items with popular attributes, leading to item exposure unfairness in recommendations. Moreover, existing approaches mostly mitigate unfairness for static recommendation models, e.g., collaborative filtering. Static models can not handle dynamic user interactions with the system that reflect users’ preferences shift through time. Thus, static models are limited in their ability to adapt to user behavior shifts to gain long-run user satisfaction. As user and item attributes are largely involved in modern recommenders and user interactions are naturally dynamic, it is essential to develop a novel method that eliminates unfairness caused by attributes meanwhile embrace the dynamic modeling of user behavior shifts. In this article, we propose Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation (Fair-HINpolicy) , which uses recent advances in context-aware off-policy learning to produce fairness-aware recommendations with rich attributes from a Heterogeneous Information Network. In particular, we formulate the off-policy learning as a Constrained Markov Decision Process (CMDP) by dynamically constraining the fairness of item exposure at each iteration. We also design an attentive action sampling to reduce the search space for off-policy learning. Our solution adaptively receives HIN-augmented corrections for counterfactual risk minimization, and ultimately yields an effective policy that maximizes long-term user satisfaction. We extensively evaluate our method through simulations on large-scale real-world datasets, obtaining favorable results compared with state-of-the-art methods.
Read moreMachine learning enabled Industrial IoT Security: Challenges, Trends and Solutions
Machine learning enabled Industrial IoT Security: Challenges, Trends and Solutions
FoPro: Few-Shot Guided Robust Webly-Supervised Prototypical Learning
Recently, webly supervised learning (WSL) has been studied to leverage numerous and accessible data from the Internet. Most existing methods focus on learning noise-robust models from web images while neglecting the performance drop caused by the differences between web domain and real-world domain. However, only by tackling the performance gap above can we fully exploit the practical value of web datasets. To this end, we propose a Few-shot guided Prototypical (FoPro) representation learning method, which only needs a few labeled examples from reality and can significantly improve the performance in the real-world domain. Specifically, we initialize each class center with few-shot real-world data as the ``realistic" prototype. Then, the intra-class distance between web instances and ``realistic" prototypes is narrowed by contrastive learning. Finally, we measure image-prototype distance with a learnable metric. Prototypes are polished by adjacent high-quality web images and involved in removing distant out-of-distribution samples. In experiments, FoPro is trained on web datasets with a few real-world examples guided and evaluated on real-world datasets. Our method achieves the state-of-the-art performance on three fine-grained datasets and two large-scale datasets. Compared with existing WSL methods under the same few-shot settings, FoPro still excels in real-world generalization. Code is available at https://github.com/yuleiqin/fopro.
Read more