Generative images have proliferated on Web platforms in social media and online copyright distribution scenarios, and semantic watermarking has increasingly been integrated into diffusion models to support reliable provenance tracking and forgery prevention for web content. Traditional noise-layer-based watermarking, however, remains vulnerable to inversion attacks that can recover embedded signals. To mitigate this, recent content-aware semantic watermarking schemes bind watermark signals to high-level image semantics, constraining local edits that would otherwise disrupt global coherence. Yet, large language models (LLMs) possess structured reasoning capabilities that enable targeted exploration of semantic spaces, allowing locally fine-grained but globally coherent semantic alterations that invalidate such bindings. To expose this overlooked vulnerability, we introduce a Coherence-Preserving Semantic Injection (CSI) attack that leverages LLM-guided semantic manipulation under embedding-space similarity constraints. This alignment enforces visual-semantic consistency while selectively perturbing watermark-relevant semantics, ultimately inducing detector misclassification. Extensive empirical results show that CSI consistently outperforms prevailing attack baselines against content-aware semantic watermarking, revealing a fundamental security weakness of current semantic watermark designs when confronted with LLM-driven semantic perturbations.

Recent advances in Large Language Models (LLMs) have raised urgent concerns about LLM-generated text authenticity, prompting regulatory demands for reliable identification mechanisms. Although watermarking offers a promising solution, existing approaches struggle to simultaneously achieve three critical requirements: text quality preservation, model-agnostic detection, and message embedding capacity, which are crucial for practical implementation. To achieve these goals, the key challenge lies in balancing the trade-off between text quality preservation and message embedding capacity. To address this challenge, we propose BiMark, a novel watermarking framework that achieves these requirements through three key innovations: (1) a bit-flip unbiased reweighting mechanism enabling model-agnostic detection, (2) a multilayer architecture enhancing detectability without compromising generation quality, and (3) an information encoding approach supporting multi-bit watermarking. Through theoretical analysis and extensive experiments, we validate that, compared to state-of-the-art multi-bit watermarking methods, BiMark achieves up to 30% higher extraction rates for short texts while maintaining text quality indicated by lower perplexity, and performs comparably to non-watermarked text on downstream tasks such as summarization and translation.

Link prediction is an important task of graph data mining that facilitates a series of applications including recommendation system, network reconstruction, etc. Node attributes make it possible to predict potential links between isolate or unobserved nodes. That attracts more and more attention of academia and industry on leveraging node attributes for link prediction. Numerous link prediction methods are based on attributed network embedding, but they are not specially designed for link prediction and may suffer potential loss of accuracy due to reduction of dimension. In this paper, we propose a direct and efficient way to utilize path-based proximity for link prediction. In many works in the past, node attributes were regarded as a different property of networks compared to heterogeneity. This paper creatively treats attributes as a distinct type of nodes and extends attributed networks to heterogeneous networks. It proposes a framework based on transition probability of meta-path guided random walks to get attributes and structure incorporated proximity of nodes. Link prediction experiments on six real-world datasets were conducted by three types of baselines methods. The experimental results demonstrates that the proposed method has exceptional performance in terms of both robustness and accuracy on most datasets.