Related papers: Improved Pseudorandom Codes from Permuted Puzzles

Watermarking is the process of embedding information into an image that can survive under distortions, while requiring the encoded image to have little or no perceptual difference from the original image. Recently, deep learning-based…

Software watermarking allows for embedding a mark into a piece of code, such that any attempt to remove the mark will render the code useless. Provably secure watermarking schemes currently seems limited to programs computing various…

Graph-structured datasets are increasingly central to sensitive applications spanning social networks, biomedical research, and cryptographic systems. As organizations share these datasets with trusted parties for collaborative analysis,…

We study a basic question about cryptographic watermarking for generative models: how reliable can a watermark remain when an adversary is allowed to corrupt the encoded signal? To address this question, we introduce a minimal coding…

Large language models now draft news, legal analyses, and software code with human-level fluency. At the same time, regulations such as the EU AI Act mandate that each synthetic passage carry an imperceptible, machine-verifiable mark for…

The indistinguishability of large language model (LLM) output from human-authored content poses significant challenges, raising concerns about potential misuse of AI-generated text and its influence on future model training. Watermarking…

The proliferation of AI-generated content brings significant concerns on the forensic and security issues such as source tracing, copyright protection, etc, highlighting the need for effective watermarking technologies. Font-based text…

There are various notions of quantum pseudorandomness, such as pseudorandom unitaries (PRUs), pseudorandom state generators (PRSGs) and pseudorandom function-like state generators (PRFSGs). Unlike classical pseudorandomness, where different…

Large language models (LLMs) have significantly enhanced the usability of AI-generated code, providing effective assistance to programmers. This advancement also raises ethical and legal concerns, such as academic dishonesty or the…

Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evaluate robustness using watermark removal attacks, these methods…

Large-language models (LLMs) are now able to produce text that is, in many cases, seemingly indistinguishable from human-generated content. This has fueled the development of watermarks that imprint a ``signal'' in LLM-generated text with…

Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based solutions are easily compromised by distortions like codec…

We propose a methodology for planting watermarks in text from an autoregressive language model that are robust to perturbations without changing the distribution over text up to a certain maximum generation budget. We generate watermarked…

Protecting intellectual property on LLM-generated code necessitates effective watermarking systems that can operate within code's highly structured, syntactically constrained nature. In this work, we introduce CodeTracer, an innovative…

A generative AI model can generate extremely realistic-looking content, posing growing challenges to the authenticity of information. To address the challenges, watermark has been leveraged to detect AI-generated content. Specifically, a…

Natural language generation (NLG) applications have gained great popularity due to the powerful deep learning techniques and large training corpus. The deployed NLG models may be stolen or used without authorization, while watermarking has…

The advancement of artificial intelligence generated content (AIGC) has created a pressing need for robust image watermarking that can withstand both conventional signal processing and novel semantic editing attacks. Current deep…

As policy catches up with the capabilities of generative AI, watermarking is central to content provenance efforts. Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization…

Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a…

Efficient knowledge injection methods for Large Language Models (LLMs), such as In-Context Learning, knowledge editing, and efficient parameter fine-tuning, significantly enhance model utility on downstream tasks. However, they also pose…