Related papers: Evaluating the Effectiveness of OpenAI's Parental …
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,…
Generative Artificial Intelligence (AI) is enabling unprecedented automation in content creation and decision support, but it also raises novel risks. This paper presents a first-principles risk assessment framework underlying the IEEE…
AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target…
As artificial intelligence (AI) systems approach and surpass expert human performance across a broad range of tasks, obtaining high-quality human supervision for evaluation and training becomes increasingly challenging. Our focus is on…
Generative AI systems are increasingly embedded in everyday life, yet empirical understanding of how psychological risk associated with AI use emerges, is experienced, and is regulated by users remains limited. We present a large-scale…
Current frontier AI safety evaluations emphasize static benchmarks, third-party annotations, and red-teaming. In this position paper, we argue that AI safety research should focus on human-centered evaluations that measure harmful…
Commercial content moderation APIs are marketed as scalable solutions to combat online hate speech. However, the reliance on these APIs risks both silencing legitimate speech, called over-moderation, and failing to protect online platforms…
Automated Speech Recognition shows superhuman performance for adult English speech on a range of benchmarks, but disappoints when fed children's speech. This has long sat in the way of child-robot interaction. Recent evolutions in…
AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) risk: an agent may execute harmful instructions embedded in untrusted inputs such as email,…
The balance between protecting users' privacy while providing cost-effective devices that are functional and usable is a key challenge in the burgeoning Internet of Things (IoT) industry. While in traditional desktop and mobile contexts the…
The emergence of AI legislation has increased the need to assess the ethical compliance of high-risk AI systems. Traditional auditing methods rely on platforms' application programming interfaces (APIs), where responses to queries are…
Voice interfaces are quickly becoming a common way for people to interact with AI systems. This also brings new security risks, such as prompt injection, social engineering, and harmful voice commands. Traditional security methods rely on…
AI emotional companions face a safety-rapport paradox: restrictive safeguards can damage supportive alliance, while permissive systems risk user harm. We present SLIP (Staged Layers of Intervention Protocol), a four-stage graduated…
Research on children's online experience and computer interaction often overlooks the relationship children have with hidden algorithms that control the content they encounter. Furthermore, it is not only about how children interact with…
Measuring personal disclosures made in human-chatbot interactions can provide a better understanding of users' AI literacy and facilitate privacy research for large language models (LLMs). We run an extensive, fine-grained analysis on the…
As large language models (LLMs) become increasingly integrated into real-world applications, scalable and rigorous safety evaluation is essential. This paper introduces Aymara AI, a programmatic platform for generating and administering…
The rapid adoption of generative AI (GenAI) chatbots has reshaped access to sexual and reproductive health (SRH) information, particularly following the overturning of Roe v. Wade, as individuals assigned female at birth increasingly turn…
Large language models have been demonstrated to be valuable in different fields. ChatGPT, developed by OpenAI, has been trained using massive amounts of data and simulates human conversation by comprehending context and generating…
Moderation layers are increasingly a core component of many products built on user- or model-generated content. However, drafting and maintaining domain-specific safety policies remains costly. We present Deep Policy Research (DPR), a…
Large language models (LLMs) are increasingly utilized in clinical reasoning and risk assessment. However, their interpretive reliability in critical and indeterminate domains such as psychiatry remains unclear. Prior work has identified…