Related papers: Watermarking Without Standards Is Not AI Governanc…
Public attention towards explainability of artificial intelligence (AI) systems has been rising in recent years to offer methodologies for human oversight. This has translated into the proliferation of research outputs, such as from…
As artificial intelligence (AI) is integrated into various services and systems in society, many companies and organizations have proposed AI principles, policies, and made the related commitments. Conversely, some have proposed the need…
Organizations of all sizes, across all industries and domains are leveraging artificial intelligence (AI) technologies to solve some of their biggest challenges around operations, customer experience, and much more. However, due to the…
Although deep neural networks have made tremendous progress in the area of multimedia representation, training neural models requires a large amount of data and time. It is well-known that utilizing trained models as initial weights often…
Safety frameworks represent a significant development in AI governance: they are the first type of publicly shared catastrophic risk management framework developed by major AI companies and focus specifically on AI scaling decisions. I…
The popularisation of applying AI in businesses poses significant challenges relating to ethical principles, governance, and legal compliance. Although businesses have embedded AI into their day-to-day processes, they lack a unified…
Watermarking is an effective way to trace model-generated content. Current watermark methods cannot resist forgery attacks, such as a deceptive claim that the model-generated content is a response to a fabricated prompt. None of them can be…
Rising concern for the societal implications of artificial intelligence systems has inspired a wave of academic and journalistic literature in which deployed systems are audited for harm by investigators from outside the organizations…
Deep neural networks are playing an important role in many real-life applications. After being trained with abundant data and computing resources, a deep neural network model providing service is endowed with economic value. An important…
This paper examines the challenge of embedding public values into national artificial intelligence (AI) governance frameworks, a task complicated by the sociotechnical nature of contemporary systems. As AI permeates domains such as…
Watermarking has emerged as a promising way to detect LLM-generated text, by augmenting LLM generations with later detectable signals. Recent work has proposed multiple families of watermarking schemes, several of which focus on preserving…
Digital Watermarking is an extremely wide aspect of information security, either by its applications, by its properties, or by its designs. In particular, a lot of research has been made about video watermarking and it can make it quite…
Oversight and control, which we collectively call supervision, are often discussed as ways to ensure that AI systems are accountable, reliable, and able to fulfill governance and management requirements. However, the requirements for "human…
Generative AI models pose a significant challenge to intellectual property (IP), as they can replicate unique artistic styles and concepts without attribution. While watermarking offers a potential solution, existing methods often fail in…
The rapid advancement of general-purpose AI models has increased concerns about copyright infringement in training data, yet current regulatory frameworks remain predominantly reactive rather than proactive. This paper examines the…
Methods for watermarking large language models have been proposed that distinguish AI-generated text from human-generated text by slightly altering the model output distribution, but they also distort the quality of the text, exposing the…
Watermarking is a technical means to dissuade malfeasant usage of Large Language Models. This paper proposes a novel watermarking scheme, so-called WaterMax, that enjoys high detectability while sustaining the quality of the generated text…
Watermarking generative models consists of planting a statistical signal (watermark) in a model's output so that it can be later verified that the output was generated by the given model. A strong watermarking scheme satisfies the property…
Recent advancements in Large Language Models (LLMs) raised concerns over potential misuse, such as for spreading misinformation. In response two counter measures emerged: machine learning-based detectors that predict if text is synthetic,…
The field of AI is undergoing a fundamental transition from generative models that can produce synthetic content to artificial agents that can plan and execute complex tasks with only limited human involvement. Companies that pioneered the…