Related papers: Mitigating Covertly Unsafe Text within Natural Lan…
Mis- and disinformation, commonly collectively called fake news, continue to menace society. Perhaps, the impact of this age-old problem is presently most plain in politics and healthcare. However, fake news is affecting an increasing…
Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…
This chapter formulates seven lessons for preventing harm in artificial intelligence (AI) systems based on insights from the field of system safety for software-based automation in safety-critical domains. New applications of AI across…
Smart toys have captured an increasing share of the toy market, and are growing ubiquitous in households with children. Smart toys are a subset of Internet of Things (IoT) devices, containing sensors, actuators, and/or artificial…
The evolution of digital communication systems and the designs of online platforms have inadvertently facilitated the subconscious propagation of toxic behavior. Giving rise to reactive responses to toxic behavior. Toxicity in online…
Large Language Models (LLMs) have emerged as a new information channel. Meanwhile, one critical but under-explored question is: Is it possible to bypass the safety alignment and inject harmful information into LLMs stealthily? In this…
While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…
As more business activities are being automated and an increasing number of computers are being used to store vital and sensitive information the need for secure computer systems becomes more apparent. These systems can be achieved only…
The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investigates the novel challenge of defending MLLMs against such…
Large Language Models (LLMs) have revolutionized content creation across digital platforms, offering unprecedented capabilities in natural language generation and understanding. These models enable beneficial applications such as content…
Recent advances in deep neural language models combined with the capacity of large scale datasets have accelerated the development of natural language generation systems that produce fluent and coherent texts (to various degrees of success)…
Detection and recognition of text in natural images are two main problems in the field of computer vision that have a wide variety of applications in analysis of sports videos, autonomous driving, industrial automation, to name a few. They…
Large pre-trained language models are often trained on large volumes of internet data, some of which may contain toxic or abusive language. Consequently, language models encode toxic information, which makes the real-world usage of these…
Recent advances in generative pre-trained transformer large language models have emphasised the potential risks of unfair use of artificial intelligence (AI) generated content in an academic environment and intensified efforts in searching…
User-generated textual contents on the Internet are often noisy, erroneous, and not in correct forms in grammar. In fact, some online users choose to express their opinions online through carefully perturbed texts, especially in…
Machine-generated texts (MGTs) produced by large language models (LLMs) are increasingly prevalent across various applications, while their potential misuse in fake news propagation and phishing has raised serious concerns, highlighting the…
Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…
Language model deployments in consumer-facing applications introduce numerous risks. While existing research on harms and hazards of such applications follows top-down approaches derived from regulatory frameworks and theoretical analyses,…
Cybersecurity incidents such as data breaches have become increasingly common, affecting millions of users and organizations worldwide. The complexity of cybersecurity threats challenges the effectiveness of existing security communication…
The proliferation of harmful content on online platforms is a major societal problem, which comes in many different forms including hate speech, offensive language, bullying and harassment, misinformation, spam, violence, graphic content,…