Generative Artificial Intelligence (AI) has increasingly been used to enhance threat intelligence and cyber security measures for organizations. Generative AI is a form of AI that creates new data without relying on existing data or expert knowledge. This technology provides decision support systems with the ability to automatically and quickly identify threats posed by hackers or malicious actors by taking into account various sources and data points. In addition, generative AI can help identify vulnerabilities within an organization s infrastructure, further reducing the potential for a successful attack. This technology is especially well-suited for security operations centers (SOCs), which require rapid identification of threats and defense measures. By incorporating interesting and valuable data points that previously would have been missed, generative AI can provide organizations with an additional layer of defense against increasingly sophisticated attacks.
Authored by Venkata Saddi, Santhosh Gopal, Abdul Mohammed, S. Dhanasekaran, Mahaveer Naruka
With the rapid advancement of technology and the expansion of available data, AI has permeated many aspects of people s lives. Large Language Models(LLMs) such as ChatGPT are increasing the accuracy of their response and achieving a high level of communication with humans. These AIs can be used in business to benefit, for example, customer support and documentation tasks, allowing companies to respond to customer inquiries efficiently and consistently. In addition, AI can generate digital content, including texts, images, and a wide range of digital materials based on the training data, and is expected to be used in business. However, the widespread use of AI also raises ethical concerns. The potential for unintentional bias, discrimination, and privacy and security implications must be carefully considered. Therefore, While AI can improve our lives, it has the potential to exacerbate social inequalities and injustices. This paper aims to explore the unintended outputs of AI and assess their impact on society. Developers and users can take appropriate precautions by identifying the potential for unintended output. Such experiments are essential to efforts to minimize the potential negative social impacts of AI transparency, accountability, and use. We will also discuss social and ethical aspects with the aim of finding sustainable solutions regarding AI.
Authored by Takuho Mitsunaga
The authors clarified in 2020 that the relationship between AI and security can be classified into four categories: (a) attacks using AI, (b) attacks by AI itself, (c) attacks to AI, and (d) security measures using AI, and summarized research trends for each. Subsequently, ChatGPT became available in November 2022, and the various potential applications of ChatGPT and other generative AIs and the associated risks have attracted attention. In this study, we examined how the emergence of generative AI affects the relationship between AI and security. The results show that (a) the need for the four perspectives of AI and security remains unchanged in the era of generative AI, (b) The generalization of AI targets and automatic program generation with the birth of generative AI will greatly increase the risk of attacks by the AI itself, (c) The birth of generative AI will make it possible to generate easy-to-understand answers to various questions in natural language, which may lead to the spread of fake news and phishing e-mails that can easily fool many people and an increase in AI-based attacks. In addition, it became clear that (1) attacks using AI and (2) responses to attacks by AI itself are highly important. Among these, the analysis of attacks by AI itself, using an attack tree, revealed that the following measures are needed: (a) establishment of penalties for developing inappropriate programs, (b) introduction of a reporting system for signs of attacks by AI, (c) measures to prevent AI revolt by incorporating Asimov s three principles of robotics, and (d) establishment of a mechanism to prevent AI from attacking humans even when it becomes confused.
Authored by Ryoichi Sasaki
Generative AI technology is being applied in various fields. However, the advancement of these technologies also raises cybersecurity issues. In fact, there are cases of cyber attack using Generative AI, and the number is increasing. Therefore, this paper analyzes the potential cybersecurity issues associated with Generative AI. First, we looked at the fields where Generative AI is used. Representatively, Generative AI is being used in text, image, video, audio, and code. Based on these five fields, cybersecurity issues that may occur in each field were analyzed. Finally, we discuss the obligations necessary for the future development and use of Generative AI.
Authored by Subin Oh, Taeshik Shon
With the rapid advancement of technology and the expansion of available data, AI has permeated many aspects of people s lives. Large Language Models(LLMs) such as ChatGPT are increasing the accuracy of their response and achieving a high level of communication with humans. These AIs can be used in business to benefit, for example, customer support and documentation tasks, allowing companies to respond to customer inquiries efficiently and consistently. In addition, AI can generate digital content, including texts, images, and a wide range of digital materials based on the training data, and is expected to be used in business. However, the widespread use of AI also raises ethical concerns. The potential for unintentional bias, discrimination, and privacy and security implications must be carefully considered. Therefore, While AI can improve our lives, it has the potential to exacerbate social inequalities and injustices. This paper aims to explore the unintended outputs of AI and assess their impact on society. Developers and users can take appropriate precautions by identifying the potential for unintended output. Such experiments are essential to efforts to minimize the potential negative social impacts of AI transparency, accountability, and use. We will also discuss social and ethical aspects with the aim of finding sustainable solutions regarding AI.
Authored by Takuho Mitsunaga
The 2023 CS curriculum by ACM, IEEE, and AAAI identifies security as an independent knowledge area that develops the “security mindset” so that students are ready for the “continual changes” in computing. Likewise, the curriculum emphasises the coverage of “uses”, and “shortcomings/pitfalls” of practical AI-tools like ChatGPT. This paper presents our endeavors to approach those goals with the design of an Information Security course. Our course design bears the following distinct features: Certificate-readiness, where we align the knowledge areas with major security/ethical hacking certificates; Coverage of ChatGPT, where the uses of ChatGPT for assisting security tasks and security issues caused by ChatGPT usage are both addressed for the first time in the teaching; “Learn defending from attackers perspective”, where labs of both offensive and defensive natures are developed to equally sharpen ethical hacking and hardening skills, and to facilitate the discussion on legal/ethical implications; Current and Representative, where ajust-enough set of representative and/or current security topics are selected in order and covered in respective modules in the most current form. In addition, we generalize our design principles and strategies, with the hope to shed lights on similar efforts in other institutions.
Authored by Yang Wang, Margaret McCoey, Qian Hu, Maryam Jalalitabar
Recent developments in generative artificial intelligence are bringing great concerns for privacy, security and misinformation. Our work focuses on the detection of fake images generated by text-to-image models. We propose a dual-domain CNN-based classifier that utilizes image features in both the spatial and frequency domain. Through an extensive set of experiments, we demonstrate that the frequency domain features facilitate high accuracy, zero-transfer learning between different generative models, and faster convergence. To our best knowledge, this is the first effective detector against generative models that are finetuned for a specific subject.
Authored by Eric Ji, Boxiang Dong, Bharath Samanthula, Na Zhou
Foundation models, such as large language models (LLMs), have been widely recognised as transformative AI technologies due to their capabilities to understand and generate content, including plans with reasoning capabilities. Foundation model based agents derive their autonomy from the capabilities of foundation models, which enable them to autonomously break down a given goal into a set of manageable tasks and orchestrate task execution to meet the goal. Despite the huge efforts put into building foundation model based agents, the architecture design of the agents has not yet been systematically explored. Also, while there are significant benefits of using agents for planning and execution, there are serious considerations regarding responsible AI related software quality attributes, such as security and accountability. Therefore, this paper presents a pattern-oriented reference architecture that serves as guidance when designing foundation model based agents. We evaluate the completeness and utility of the proposed reference architecture by mapping it to the architecture of two real-world agents.
Authored by Qinghua Lu, Liming Zhu, Xiwei Xu, Zhenchang Xing, Stefan Harrer, Jon Whittle
In this work, we leverage the pure skin color patch from the face image as the additional information to train an auxiliary skin color feature extractor and face recognition model in parallel to improve performance of state-of-the-art (SOTA) privacy-preserving face recognition (PPFR) systems. Our solution is robust against black-box attacking and well-established generative adversarial network (GAN) based image restoration. We analyze the potential risk in previous work, where the proposed cosine similarity computation might directly leak the protected precomputed embedding stored on the server side. We propose a Function Secret Sharing (FSS) based face embedding comparison protocol without any intermediate result leakage. In addition, we show in experiments that the proposed protocol is more efficient compared to the Secret Sharing (SS) based protocol.
Authored by Dong Han, Yufan Jiang, Yong Li, Ricardo Mendes, Joachim Denzler
The authors clarified in 2020 that the relationship between AI and security can be classified into four categories: (a) attacks using AI, (b) attacks by AI itself, (c) attacks to AI, and (d) security measures using AI, and summarized research trends for each. Subsequently, ChatGPT became available in November 2022, and the various potential applications of ChatGPT and other generative AIs and the associated risks have attracted attention. In this study, we examined how the emergence of generative AI affects the relationship between AI and security. The results show that (a) the need for the four perspectives of AI and security remains unchanged in the era of generative AI, (b) The generalization of AI targets and automatic program generation with the birth of generative AI will greatly increase the risk of attacks by the AI itself, (c) The birth of generative AI will make it possible to generate easy-to-understand answers to various questions in natural language, which may lead to the spread of fake news and phishing e-mails that can easily fool many people and an increase in AI-based attacks. In addition, it became clear that (1) attacks using AI and (2) responses to attacks by AI itself are highly important. Among these, the analysis of attacks by AI itself, using an attack tree, revealed that the following measures are needed: (a) establishment of penalties for developing inappropriate programs, (b) introduction of a reporting system for signs of attacks by AI, (c) measures to prevent AI revolt by incorporating Asimov s three principles of robotics, and (d) establishment of a mechanism to prevent AI from attacking humans even when it becomes confused.
Authored by Ryoichi Sasaki
With the rapid advancement of technology and the expansion of available data, AI has permeated many aspects of people s lives. Large Language Models(LLMs) such as ChatGPT are increasing the accuracy of their response and achieving a high level of communication with humans. These AIs can be used in business to benefit, for example, customer support and documentation tasks, allowing companies to respond to customer inquiries efficiently and consistently. In addition, AI can generate digital content, including texts, images, and a wide range of digital materials based on the training data, and is expected to be used in business. However, the widespread use of AI also raises ethical concerns. The potential for unintentional bias, discrimination, and privacy and security implications must be carefully considered. Therefore, While AI can improve our lives, it has the potential to exacerbate social inequalities and injustices. This paper aims to explore the unintended outputs of AI and assess their impact on society. Developers and users can take appropriate precautions by identifying the potential for unintended output. Such experiments are essential to efforts to minimize the potential negative social impacts of AI transparency, accountability, and use. We will also discuss social and ethical aspects with the aim of finding sustainable solutions regarding AI.
Authored by Takuho Mitsunaga
The emergence of large language models (LLMs) has brought forth remarkable capabilities in various domains, yet it also poses inherent risks to trustfulness, encompassing concerns such as toxicity, stereotype bias, adversarial robustness, ethics, privacy, and fairness. Particularly in sensitive applications like customer support chatbots, AI assistants, and digital information automation, which handle privacy-sensitive data, the adoption of generative pre-trained transformer (GPT) models is pervasive. However, ensuring robust security measures to mitigate potential security vulnerabilities is imperative. This paper advocates for a proactive approach termed "security shift-left," which emphasizes integrating security measures early in the development lifecycle to bolster the security posture of LLM-based applications. Our proposed method leverages basic machine learning (ML) techniques and retrieval-augmented generation (RAG) to effectively address security concerns. We present empirical evidence validating the efficacy of our approach with one LLM-based security application designed for the detection of malicious intent, utilizing both open-source datasets and synthesized datasets. By adopting this security shift-left methodology, developers can confidently develop LLM-based applications with robust security protection, safeguarding against potential threats and vulnerabilities.
Authored by Qianlong Lan, Anuj Kaul, Nishant Pattanaik, Piyush Pattanayak, Vinothini Pandurangan
The advent of Generative AI has marked a significant milestone in artificial intelligence, demonstrating remarkable capabilities in generating realistic images, texts, and data patterns. However, these advancements come with heightened concerns over data privacy and copyright infringement, primarily due to the reliance on vast datasets for model training. Traditional approaches like differential privacy, machine unlearning, and data poisoning only offer fragmented solutions to these complex issues. Our paper delves into the multifaceted challenges of privacy and copyright protection within the data lifecycle. We advocate for integrated approaches that combines technical innovation with ethical foresight, holistically addressing these concerns by investigating and devising solutions that are informed by the lifecycle perspective. This work aims to catalyze a broader discussion and inspire concerted efforts towards data privacy and copyright integrity in Generative AI.CCS CONCEPTS• Software and its engineering Software architectures; • Information systems World Wide Web; • Security and privacy Privacy protections; • Social and professional topics Copyrights; • Computing methodologies Machine learning.
Authored by Dawen Zhang, Boming Xia, Yue Liu, Xiwei Xu, Thong Hoang, Zhenchang Xing, Mark Staples, Qinghua Lu, Liming Zhu
With the rapid growth in information technology and being called the Digital Era, it is very evident that no one can survive without internet or ICT advancements. The day-to-day life operations and activities are dependent on these technologies. The latest technology trends in the market and industry are computing power, Smart devices, artificial intelligence, Robotic process automation, metaverse, IOT (Internet of things), cloud computing, Edge computing, Block chain and much more in the coming years. When looking at all these aspect and advancements, one common thing is cloud computing and data which must be protected and safeguarded which brings in the need for cyber/cloud security. Hence cloud security challenges have become an omnipresent concern for organizations or industries of any size where it has gone from a small incident to threat landscape. When it comes to data and cyber/ cloud security there are lots of challenges seen to safeguard these data. Towards that it is necessary that everyone must be aware of the latest technological advancements, evolving cyber threats, data as a valuable asset, Human Factor, Regulatory compliance, Cyber resilience. To handle all these challenges, security and risk prediction framework is proposed in this paper. This framework PRCSAM (Predictive Risk and Complexity Score Assessment Model) will consider factors like impact and likelihood of the main risks, threats and attacks that is foreseen in cloud security and the recommendation of the Risk management framework with automatic risk assessment and scoring option catering to Information security and privacy risks. This framework will help management and organizations in making informed decisions on the cyber security strategy as this is a data driven, dynamic \& proactive approach to cyber security and its complexity calculation. This paper also discusses on the prediction techniques using Generative AI techniques.
Authored by Kavitha Ayappan, J.M Mathana, J Thangakumar
The authors clarified in 2020 that the relationship between AI and security can be classified into four categories: (a) attacks using AI, (b) attacks by AI itself, (c) attacks to AI, and (d) security measures using AI, and summarized research trends for each. Subsequently, ChatGPT became available in November 2022, and the various potential applications of ChatGPT and other generative AIs and the associated risks have attracted attention. In this study, we examined how the emergence of generative AI affects the relationship between AI and security. The results show that (a) the need for the four perspectives of AI and security remains unchanged in the era of generative AI, (b) The generalization of AI targets and automatic program generation with the birth of generative AI will greatly increase the risk of attacks by the AI itself, (c) The birth of generative AI will make it possible to generate easy-to-understand answers to various questions in natural language, which may lead to the spread of fake news and phishing e-mails that can easily fool many people and an increase in AI-based attacks. In addition, it became clear that (1) attacks using AI and (2) responses to attacks by AI itself are highly important. Among these, the analysis of attacks by AI itself, using an attack tree, revealed that the following measures are needed: (a) establishment of penalties for developing inappropriate programs, (b) introduction of a reporting system for signs of attacks by AI, (c) measures to prevent AI revolt by incorporating Asimov s three principles of robotics, and (d) establishment of a mechanism to prevent AI from attacking humans even when it becomes confused.
Authored by Ryoichi Sasaki
With the rapid advancement of technology and the expansion of available data, AI has permeated many aspects of people s lives. Large Language Models(LLMs) such as ChatGPT are increasing the accuracy of their response and achieving a high level of communication with humans. These AIs can be used in business to benefit, for example, customer support and documentation tasks, allowing companies to respond to customer inquiries efficiently and consistently. In addition, AI can generate digital content, including texts, images, and a wide range of digital materials based on the training data, and is expected to be used in business. However, the widespread use of AI also raises ethical concerns. The potential for unintentional bias, discrimination, and privacy and security implications must be carefully considered. Therefore, While AI can improve our lives, it has the potential to exacerbate social inequalities and injustices. This paper aims to explore the unintended outputs of AI and assess their impact on society. Developers and users can take appropriate precautions by identifying the potential for unintended output. Such experiments are essential to efforts to minimize the potential negative social impacts of AI transparency, accountability, and use. We will also discuss social and ethical aspects with the aim of finding sustainable solutions regarding AI.
Authored by Takuho Mitsunaga
Generative Artificial Intelligence (AI) has increasingly been used to enhance threat intelligence and cyber security measures for organizations. Generative AI is a form of AI that creates new data without relying on existing data or expert knowledge. This technology provides decision support systems with the ability to automatically and quickly identify threats posed by hackers or malicious actors by taking into account various sources and data points. In addition, generative AI can help identify vulnerabilities within an organization s infrastructure, further reducing the potential for a successful attack. This technology is especially well-suited for security operations centers (SOCs), which require rapid identification of threats and defense measures. By incorporating interesting and valuable data points that previously would have been missed, generative AI can provide organizations with an additional layer of defense against increasingly sophisticated attacks.
Authored by Venkata Saddi, Santhosh Gopal, Abdul Mohammed, S. Dhanasekaran, Mahaveer Naruka
In the ever-changing world of blockchain technology, the emergence of smart contracts has completely transformed the way agreements are executed, offering the potential for automation and trust in decentralized systems. Despite their built-in security features, smart contracts still face persistent vulnerabilities, resulting in significant financial losses. While existing studies often approach smart contract security from specific angles, such as development cycles or vulnerability detection tools, this paper adopts a comprehensive, multidimensional perspective. It delves into the intricacies of smart contract security by examining vulnerability detection mechanisms and defense strategies. The exploration begins by conducting a detailed analysis of the current security challenges and issues surrounding smart contracts. It then delves into established frameworks for classifying vulnerabilities and common security flaws. The paper examines existing methods for detecting, and repairing contract vulnerabilities, evaluating their effectiveness. Additionally, it provides a comprehensive overview of the existing body of knowledge in smart contract security-related research. Through this systematic examination, the paper aims to serve as a valuable reference and provide a comprehensive understanding of the multifaceted landscape of smart contract security.
Authored by Nayantara Kumar, Niranjan Honnungar V, Sharwari Prakash, J Lohith
Significant progress has been made towards developing Deep Learning (DL) in Artificial Intelligence (AI) models that can make independent decisions. However, this progress has also highlighted the emergence of malicious entities that aim to manipulate the outcomes generated by these models. Due to increasing complexity, this is a concerning issue in various fields, such as medical image classification, autonomous vehicle systems, malware detection, and criminal justice. Recent research advancements have highlighted the vulnerability of these classifiers to both conventional and adversarial assaults, which may skew their results in both the training and testing stages. The Systematic Literature Review (SLR) aims to analyse traditional and adversarial attacks comprehensively. It evaluates 45 published works from 2017 to 2023 to better understand adversarial attacks, including their impact, causes, and standard mitigation approaches.
Authored by Tarek Ali, Amna Eleyan, Tarek Bejaoui
Attacks against computer system are viewed to be the most serious threat in the modern world. A zero-day vulnerability is an unknown vulnerability to the vendor of the system. Deep learning techniques are widely used for anomaly-based intrusion detection. The technique gives a satisfactory result for known attacks but for zero-day attacks the models give contradictory results. In this work, at first, two separate environments were setup to collect training and test data for zero-day attack. Zero-day attack data were generated by simulating real-time zero-day attacks. Ranking of the features from the train and test data was generated using explainable AI (XAI) interface. From the collected training data more attack data were generated by applying time series generative adversarial network (TGAN) for top 12 features. The train data was concatenated with the AWID dataset. A hybrid deep learning model using Long short-term memory (LSTM) and Convolutional neural network (CNN) was developed to test the zero-day data against the GAN generated concatenated dataset and the original AWID dataset. Finally, it was found that the result using the concatenated dataset gives better performance with 93.53\% accuracy, where the result from only AWID dataset gives 84.29\% accuracy.
Authored by Md. Asaduzzaman, Md. Rahman
As a recent breakthrough in generative artificial intelligence, ChatGPT is capable of creating new data, images, audio, or text content based on user context. In the field of cybersecurity, it provides generative automated AI services such as network detection, malware protection, and privacy compliance monitoring. However, it also faces significant security risks during its design, training, and operation phases, including privacy breaches, content abuse, prompt word attacks, model stealing attacks, abnormal structure attacks, data poisoning attacks, model hijacking attacks, and sponge attacks. This paper starts from the risks and events that ChatGPT has recently faced, proposes a framework for analyzing cybersecurity in cyberspace, and envisions adversarial models and systems. It puts forward a new evolutionary relationship between attackers and defenders using ChatGPT to enhance their own capabilities in a changing environment and predicts the future development of ChatGPT from a security perspective.
Authored by Chunhui Hu, Jianfeng Chen
XAI with natural language processing aims to produce human-readable explanations as evidence for AI decision-making, which addresses explainability and transparency. However, from an HCI perspective, the current approaches only focus on delivering a single explanation, which fails to account for the diversity of human thoughts and experiences in language. This paper thus addresses this gap, by proposing a generative XAI framework, INTERACTION (explain aNd predicT thEn queRy with contextuAl CondiTional varIational autO-eNcoder). Our novel framework presents explanation in two steps: (step one) Explanation and Label Prediction; and (step two) Diverse Evidence Generation. We conduct intensive experiments with the Transformer architecture on a benchmark dataset, e-SNLI [1]. Our method achieves competitive or better performance against state-of-the-art baseline models on explanation generation (up to 4.7% gain in BLEU) and prediction (up to 4.4% gain in accuracy) in step one; it can also generate multiple diverse explanations in step two.
Authored by Jialin Yu, Alexandra Cristea, Anoushka Harit, Zhongtian Sun, Olanrewaju Aduragba, Lei Shi, Noura Moubayed
Due to the simplicity of implementation and high threat level, SQL injection attacks are one of the oldest, most prevalent, and most destructive types of security attacks on Web-based information systems. With the continuous development and maturity of artificial intelligence technology, it has been a general trend to use AI technology to detect SQL injection. The selection of the sample set is the deciding factor of whether AI algorithms can achieve good results, but dataset with tagged specific category labels are difficult to obtain. This paper focuses on data augmentation to learn similar feature representations from the original data to improve the accuracy of classification models. In this paper, deep convolutional generative adversarial networks combined with genetic algorithms are applied to the field of Web vulnerability attacks, aiming to solve the problem of insufficient number of SQL injection samples. This method is also expected to be applied to sample generation for other types of vulnerability attacks.
Authored by Dongzhe Lu, Jinlong Fei, Long Liu, Zecun Li
Due to the migration megatrend, efficient and effective second-language acquisition is vital. One proposed solution involves AI-enabled conversational agents for person-centered interactive language practice. We present results from ongoing action research targeting quality assurance of proprietary generative dialog models trained for virtual job interviews. The action team elicited a set of 38 requirements for which we designed corresponding automated test cases for 15 of particular interest to the evolving solution. Our results show that six of the test case designs can detect meaningful differences between candidate models. While quality assurance of natural language processing applications is complex, we provide initial steps toward an automated framework for machine learning model selection in the context of an evolving conversational agent. Future work will focus on model selection in an MLOps setting.
Authored by Markus Borg, Johan Bengtsson, Harald Österling, Alexander Hagelborn, Isabella Gagner, Piotr Tomaszewski