Related papers: NLP Security and Ethics, in the Wild

Cyber security has become an issue of national concern in the UK, USA and many other countries worldwide. Universities have reacted to this by launching numerous cyber security degree programmes. In this paper we explore the structure of…

Language technologies have made enormous progress, especially with the introduction of large language models (LLMs). On traditional tasks such as machine translation and sentiment analysis, these models perform at near-human level. These…

Online Social Networks (OSNs) have rapidly become a prominent and widely used service, offering a wealth of personal and sensitive information with significant security and privacy implications. Hence, OSNs are also an important - and…

Natural Language Processing (NLP) has become a cornerstone in many critical sectors, including healthcare, finance, and customer relationship management. This is especially true with the development and use of advanced models such as…

While large language models (LLMs) present significant potential for supporting numerous real-world applications and delivering positive social impacts, they still face significant challenges in terms of the inherent risk of privacy…

Large language models (LLMs) are increasingly prevalent in security research. Their unique characteristics, however, introduce challenges that undermine established paradigms of reproducibility, rigor, and evaluation. Prior work has…

Recent research on large language models (LLMs) has demonstrated their ability to understand and employ deceptive behavior, even without explicit prompting. However, such behavior has only been observed in rare, specialized cases and has…

While we have witnessed a rapid growth of ethics documents meant to guide AI development, the promotion of AI ethics has nonetheless proceeded with little input from AI practitioners themselves. Given the proliferation of AI for Social Good…

Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly…

Human-Centric NLP often claims to prioritise human needs and values, yet many implementations reveal an underlying AI-centric focus. Through an analysis of case studies in language modelling, behavioural testing, and multi-modal alignment,…

As NLP systems are increasingly deployed at scale, concerns about their potential negative impacts have attracted the attention of the research community, yet discussions of risk have mostly been at an abstract level and focused on generic…

Large Language Models (LLMs) have demonstrated potential in cybersecurity applications but have also caused lower confidence due to problems like hallucinations and a lack of truthfulness. Existing benchmarks provide general evaluations but…

This paper explores the distinctions and connections between cybersecurity and ethical hacking, two vital disciplines in the protection of digital systems. It defines each field, outlines their goals and methodologies, and compares the…

This paper aims to shed light on the ethical problems of creating and deploying computer vision tech, particularly in using publicly available datasets. Due to the rapid growth of machine learning and artificial intelligence, computer…

Since a significant time ago, although time runs very fast,nanotechnology transformed from one of the most promising scientific hopes in uncountable human domains into a marvelous certainty. Innumerable scientific studies in several areas…

As people across the world become increasingly aware of how their privacy is compromised in this digital era, the field of Privacy Enhancing Technologies, or PETs, has boomed. The first workshop on Privacy Enhancing Technology was in 2000,…

Extremism research has grown as an open problem for several countries during recent years, especially due to the apparition of movements such as jihadism. This and other extremist groups have taken advantage of different approaches, such as…

In recent years, we have witnessed a marked development and growth in Artificial Intelligence. The growth of the data volume generated by sensors and machines, combined with the information flow resulting from the user actions on the…

In deployment and application, large language models (LLMs) typically undergo safety alignment to prevent illegal and unethical outputs. However, the continuous advancement of jailbreak attack techniques, designed to bypass safety…

Large Language Models (LLMs), such as ChatGPT and Bard, have revolutionized natural language understanding and generation. They possess deep language comprehension, human-like text generation capabilities, contextual awareness, and robust…