相关论文: Permute-and-Flip: An optimally stable and watermar…

Typically, foundation models are hosted on cloud servers to meet the high demand for their services. However, this exposes them to security risks, as attackers can modify them after uploading to the cloud or transferring from a local…

Benefiting from performance advantages under short code lengths, polar codes are well-suited for certain scenarios, such as the future Internet of Things (IoT) applications that require high reliability and low power. Existing list flip…

The growing deployment of Large Language Models (LLMs) has raised concerns about their misuse in generating harmful or deceptive content. To address this issue, watermarking methods have been proposed to embed identifiable multi-bit…

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…

Large language models (LLMs) have show great ability in various natural language tasks. However, there are concerns that LLMs are possible to be used improperly or even illegally. To prevent the malicious usage of LLMs, detecting…

In the domain of software watermarking, we have proposed several graph theoretic watermarking codec systems for encoding watermark numbers $w$ as reducible permutation flow-graphs $F[\pi^*]$ through the use of self-inverting permutations…

We address in this paper decoding aspects of the Compute-and-Forward (CF) physical-layer network coding strategy. It is known that the original decoder for the CF is asymptotically optimal. However, its performance gap to optimal decoders…

In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are growing concerns that the current LLM watermarking schemes are…

Watermarking is a technique that involves embedding nearly unnoticeable statistical signals within generated content to help trace its source. This work focuses on a scenario where an untrusted third-party user sends prompts to a trusted…

In this paper, a robust and blind watermarking method is proposed, which is highly resistant to the common image watermarking attacks, such as noises, compression, and image quality enhancement processing. In this method, Arnold Cat map is…

Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing watermarking detection techniques primarily focus on classifying…

As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effective strategy for mitigating such harms by enabling the…

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…

The rapid growth of transformer-based models increases the concerns about their integrity and ownership insurance. Watermarking addresses this issue by embedding a unique identifier into the model, while preserving its performance. However,…

The current paper presents a robust watermarking method for still images, which uses the similarity of discrete wavelet transform and human visual system (HVS). The proposed scheme makes the use of pixel wise masking in order to make binary…

Positional encoding (PE) underpins how permutation-invariant Transformers represent sequence order, yet how positional information is processed and stored remains poorly understood. Modern PE methods such as RoPE still struggle on tasks…

The rapid advancement of LLMs (Large Language Models) has established them as a foundational technology for many AI and ML-powered human computer interactions. A critical challenge in this context is the attribution of LLM-generated text --…

Deep learning based blind watermarking works have gradually emerged and achieved impressive performance. However, previous deep watermarking studies mainly focus on fixed low-resolution images while paying less attention to arbitrary…

Number-conserved subspace encoding reduces resources needed for quantum simulations, but scalable complexity trade-off bounds for $M$ modes and $N$ particles with $\mathcal{O}(N\log M)$ qubits have remained unknown. We study…

Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models -- in principle, the watermark should be preserved when an…