Related papers: Mitigating Covertly Unsafe Text within Natural Lan…

The purpose of the study is to supplement and update the list of threats to the confidentiality and integrity of the system. The article focuses on the already compiled list of threats and a model of system, but also considers new threats…

Toxicity on the Internet, such as hate speech, offenses towards particular users or groups of people, or the use of obscene words, is an acknowledged problem. However, there also exist other types of inappropriate messages which are usually…

Pervasive personal communication technologies offer the potential for important social benefits for individual users, but also the potential for significant social difficulties and costs. In research on face-to-face social interaction,…

Despite the impressive capabilities of Large Language Models (LLMs) in various tasks, their vulnerability to unsafe prompts remains a critical issue. These prompts can lead LLMs to generate responses on illegal or sensitive topics, posing a…

Humans are susceptible to undesirable behaviours and privacy leaks under the influence of alcohol. This paper investigates drunk language, i.e., text written under the influence of alcohol, as a driver for safety failures in large language…

With the ability to generate high-quality images, text-to-image (T2I) models can be exploited for creating inappropriate content. To prevent misuse, existing safety measures are either based on text blacklists, which can be easily…

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…

The prevalence of short form video platforms, combined with the ineffectiveness of age verification mechanisms, raises concerns about the potential harms facing children and teenagers in an algorithm-moderated online environment. We…

Threat modelling is the process of identifying potential vulnerabilities in a system and prioritising them. Existing threat modelling tools focus primarily on technical systems and are not as well suited to interpersonal threats. In this…

Speech technology for communication, accessing information, and services has rapidly improved in quality. It is convenient and appealing because speech is the primary mode of communication for humans. Such technology, however, also presents…

Autonomous systems are emerging in many application domains. With the recent advancements in artificial intelligence and machine learning, sensor technology, perception algorithms and robotics, scenarios previously requiring strong human…

Despite advances in large language model capabilities in recent years, a large gap remains in their capabilities and safety performance for many languages beyond a relatively small handful of globally dominant languages. This paper provides…

Modifying characters of a piece of text to their visual similar ones often ap-pear in spam in order to fool inspection systems and other conditions, which we regard as a kind of adversarial attack to neural models. We pro-pose a way of…

This paper investigates a problem about freedom of information. Although freedom of information is generally considered desirable, there are a number of areas where there is substantial agreement that freedom of information should be…

Toxicity detection algorithms, originally designed with reactive content moderation in mind, are increasingly being deployed into proactive end-user interventions to moderate content. Through a socio-technical lens and focusing on contexts…

In this work, we study a critical research problem regarding the trustworthiness of large language models (LLMs): how LLMs behave when encountering ambiguous narrative text, with a particular focus on Chinese textual ambiguity. We created a…

A decade after its first release, the Go programming language has become a major programming language in the development landscape. While praised for its clean syntax and C-like performance, Go also contains a strong static type-system that…

Online platforms have become an increasingly prominent means of communication. Despite the obvious benefits to the expanded distribution of content, the last decade has resulted in disturbing toxic communication, such as cyberbullying and…

AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these…

Controlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. Many approaches reduce this problem to training a predictor of the desired attribute. For example, researchers hoping…