相关论文: Where's the Liability in Harmful AI Speech?

The rapidity with which generative AI has been adopted and advanced has raised legal and ethical questions related to the impact on artists rights, content production, data collection, privacy, accuracy of information, and intellectual…

Agentic Artificial Intelligence (AI) can autonomously pursue long-term goals, make decisions, and execute complex, multi-turn workflows. Unlike traditional generative AI, which responds reactively to prompts, agentic AI proactively…

Amidst the growing interest in developing task-autonomous AI for automated mental health care, this paper addresses the ethical and practical challenges associated with the issue and proposes a structured framework that delineates levels of…

As generative AI (GenAI) agents become more common in enterprise settings, they introduce security challenges that differ significantly from those posed by traditional systems. These agents are not just LLMs; they reason, remember, and act,…

As generative AI technologies find more and more real-world applications, the importance of testing their performance and safety seems paramount. "Red-teaming" has quickly become the primary approach to test AI models--prioritized by AI…

Generative artificial intelligence (AI) systems are trained on large data corpora to generate new pieces of text, images, videos, and other media. There is growing concern that such systems may infringe on the copyright interests of…

Large language models (LLMs) are increasingly integrated into a variety of writing tasks. While these tools can help people by generating ideas or producing higher quality work, like many other AI tools they may risk causing a variety of…

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,…

Generative AI systems produce a range of risks. To ensure the safety of generative AI systems, these risks must be evaluated. In this paper, we make two main contributions toward establishing such evaluations. First, we propose a…

The rapid proliferation of multimodal generative models has sparked critical discussions on their reliability, fairness and potential for misuse. While text-to-image models excel at producing high-fidelity, user-guided content, they often…

In the rapidly advancing field of artificial intelligence, the concept of Red-Teaming or Jailbreaking large language models (LLMs) has emerged as a crucial area of study. This approach is especially significant in terms of assessing and…

Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety…

This paper challenges the assumption that courts should grant First Amendment protections to outputs from large generative AI models, such as GPT-4 and Gemini. We argue that because these models lack intentionality, their outputs do not…

AI-powered greenwashing has emerged as an insidious challenge within corporate sustainability governance, exacerbating the opacity of environmental disclosures and subverting regulatory oversight. This study conducts a comparative legal…

While state-of-the-art language models have achieved impressive results, they remain susceptible to inference-time adversarial attacks, such as adversarial prompts generated by red teams arXiv:2209.07858. One approach proposed to improve…

Rapid progress in general-purpose AI has sparked significant interest in "red teaming," a practice of adversarial testing originating in military and cybersecurity applications. AI red teaming raises many questions about the human factor,…

Large Language Models (LLMs) are increasingly utilized for mental health support; however, current safety benchmarks often fail to detect the complex, longitudinal risks inherent in therapeutic dialogue. We introduce an evaluation framework…

As AI systems become prevalent in high stakes domains such as surveillance and healthcare, researchers now examine how to design and implement them in a safe manner. However, the potential harms caused by systems to stakeholders in complex…

Many safety post-training methods for large language models (LLMs) are designed to modify the model's behaviour from producing unsafe answers to issuing refusals. However, such distribution shifts are often brittle and degrade performance…

As generative large model capabilities advance, safety concerns become more pronounced in their outputs. To ensure the sustainable growth of the AI ecosystem, it's imperative to undertake a holistic evaluation and refinement of associated…