Related papers: EmbTracker: Traceable Black-box Watermarking for F…

Large Language Models (LLMs) are rapidly transforming the landscape of digital content creation. However, the prevalent black-box Application Programming Interface (API) access to many LLMs introduces significant challenges in…

Safeguarding the intellectual property of machine learning models has emerged as a pressing concern in AI security. Model watermarking is a powerful technique for protecting ownership of machine learning models, yet its reliability has been…

Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decoding to embed watermarks, which compromises the availability…

The rapid development of Large Language Models (LLMs) has intensified concerns about content traceability and potential misuse. Existing watermarking schemes for sampled text often face trade-offs between maintaining text quality and…

Proprietary large language models (LLMs) face risks of intellectual property (IP) violation, as adversaries can replicate an LLM by collecting input-output pairs to train a surrogate model, causing financial setbacks. Watermarks offer a…

Embeddings are functions that map raw input data to low-dimensional vector representations, while preserving important semantic information about the inputs. Pre-training embeddings on a large amount of unlabeled data and fine-tuning them…

Various threats posed by the progress in text-to-speech (TTS) have prompted the need to reliably trace synthesized speech. However, contemporary approaches to this task involve adding watermarks to the audio separately after generation, a…

With the widespread use of deep neural networks (DNNs) in many areas, more and more studies focus on protecting DNN models from intellectual property (IP) infringement. Many existing methods apply digital watermarking to protect the DNN…

With the increasing use of large language models (LLMs) in daily life, concerns have emerged regarding their potential misuse and societal impact. Watermarking is proposed to trace the usage of specific models by injecting patterns into…

As a self-supervised learning paradigm, contrastive learning has been widely used to pre-train a powerful encoder as an effective feature extractor for various downstream tasks. This process requires numerous unlabeled training data and…

Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compression and noise addition), we reveal a fundamental…

The rapid advancement of generative AI has made it increasingly challenging to distinguish between deepfake audio and authentic human speech. To overcome the limitations of passive detection methods, we propose StreamMark, a novel deep…

We propose an imperceptible multi-bit text watermark embedded by paraphrasing with LLMs. We fine-tune a pair of LLM paraphrasers that are designed to behave differently so that their paraphrasing difference reflected in the text semantics…

Generative code models (GCMs) significantly enhance development efficiency through automated code generation and code summarization. However, building and training these models require computational resources and time, necessitating…

Large language model (LLM) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming robustness against paraphrasing and text editing. In this paper, we argue that existing evaluations…

Being trained on large and diverse datasets, visual foundation models (VFMs) can be fine-tuned to achieve remarkable performance and efficiency in various downstream computer vision tasks. The high computational cost of data collection and…

Watermarking has emerged as a promising solution for tracing and authenticating text generated by large language models (LLMs). A common approach to LLM watermarking is to construct a green/red token list and assign higher or lower…

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…

Federated Learning (FL) is a privacy-preserving distributed machine learning scheme, where each participant data remains on the participating devices and only the local model generated utilizing the local computational power is transmitted…

The proliferation of Deep Neural Networks (DNN) in commercial applications is expanding rapidly. Simultaneously, the increasing complexity and cost of training DNN models have intensified the urgency surrounding the protection of…