Related papers: Evaluating AI-Enabled deception vulnerability amon…
AI-based systems, including Large Language Models (LLM), impact millions by supporting diverse tasks but face issues like misinformation, bias, and misuse. AI ethics is crucial as new technologies and concerns emerge, but objective,…
Powerful new frontier AI technologies are bringing many benefits to society but at the same time bring new risks. AI developers and regulators are therefore seeking ways to assure the safety of such systems, and one promising method under…
As generative AI is increasingly contributing to the spread of deceptively realistic misinformation, lawmakers have introduced regulations requiring the disclosure of AI-generated content. However, it is unclear if labels reduce the risk of…
With the recent advent of Large Language Models (LLMs), such as ChatGPT from OpenAI, BARD from Google, Llama2 from Meta, and Claude from Anthropic AI, gain widespread use, ensuring their security and robustness is critical. The widespread…
This paper provides a comprehensive literature review on the belief in false information, including misinformation, disinformation, and fake information. It addresses the increasing societal concern regarding false information, which is…
Speech AI Technologies are largely trained on publicly available datasets or by the massive web-crawling of speech. In both cases, data acquisition focuses on minimizing collection effort, without necessarily taking the data subjects'…
We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…
Social engineering (SE) attacks remain a significant threat to both individuals and organizations. The advancement of Artificial Intelligence (AI), including diffusion models and large language models (LLMs), has potentially intensified…
Susceptibility to misinformation describes the degree of belief in unverifiable claims, a latent aspect of individuals' mental processes that is not observable. Existing susceptibility studies heavily rely on self-reported beliefs, which…
While substantial efforts in anti-trafficking research and practice have focused on identifying and assisting victims after exploitation occurs, comparatively less attention has been paid to preventing victimization at the recruitment…
With the rapid diffusion of social networks in combination with mobile phones, a new social threat of sextortion has emerged, in which vulnerable young women are essentially blackmailed with their explicit shared multimedia content. The…
The scope of AI safety and alignment work in generative artificial intelligence (GenAI) has so far mostly been limited to harms related to: (a) discrimination and hate speech, (b) harmful/inappropriate (violent, sexual, illegal) content,…
AI risk assessment is the primary tool for identifying harms caused by AI systems. These include intersectional harms, which arise from the interaction between identity categories (e.g., class and skin tone) and which do not occur, or occur…
Artificial Intelligence (AI) tools have become incredibly powerful in generating synthetic images. Of particular concern are generated images that resemble photographs as they aspire to represent real world events. Synthetic photographs may…
In recent studies of political decision-making, apparently anomalous behavior has been observed on the part of voters, in which negative information about a candidate strengthens, rather than weakens, a prior positive opinion about the…
A common assumption in the social learning literature is that agents exchange information in an unselfish manner. In this work, we consider the scenario where a subset of agents aims at deceiving the network, meaning they aim at driving the…
Bias detection and mitigation is an active area of research in machine learning. This work extends previous research done by the authors to provide a rigorous and more complete analysis of the bias found in AI predictive models. Admissions…
Recent studies have demonstrated that deep learning models can discriminate based on protected classes like race and gender. In this work, we evaluate bias present in deepfake datasets and detection models across protected subgroups. Using…
Financial institutions increasingly rely on large language models (LLMs) for high-stakes decision-making. However, these models risk perpetuating harmful biases if deployed without careful oversight. This paper investigates racial bias in…
Deceptive news posts shared in online communities can be detected with NLP models, and much recent research has focused on the development of such models. In this work, we use characteristics of online communities and authors -- the context…