Jing Wang
Author directoryOther people with similar names: Jing Wang, Jing Wang, Jing Wang, Jing Wang, Jing Wang
Unverified author pages with similar names: Jing Wang
2026
HSPMark: Desynchronization-Resilient Multi-Bit LLM Watermarking via Semantic Anchoring
Jing Wang | Pengyu Xiong | Kejun Qian | Yi Yang | Jing Fan
Findings of the Association for Computational Linguistics: EMNLP 2026
Jing Wang | Pengyu Xiong | Kejun Qian | Yi Yang | Jing Fan
Findings of the Association for Computational Linguistics: EMNLP 2026
Reliable multi-bit watermarking is essential for tracing the provenance of large language model (LLM) outputs. However, existing high-capacity schemes typically synchronize pseudo-random functions through discrete token n-gram matching, which makes them vulnerable to desynchronization under semantics-preserving paraphrasing attacks. To address this issue, we propose HSPMark, a hierarchical semantic projection marking mechanism for context-aware multi-bit watermarking, which shifts watermark synchronization from brittle token histories to continuous semantic anchors. HSPMark extracts stable contextual features using a pre-trained sentence-level encoder and a lightweight Robust Semantic MLP, then projects these features into context-conditioned pseudo-orthogonal bias matrices for multi-bit payload injection. To balance payload capacity and generation quality, HSPMark introduces an entropy-adaptive embedding mechanism that modulates logit bias according to predictive uncertainty. Extensive evaluations demonstrate that HSPMark improves robustness against paraphrase-induced desynchronization and local perturbations while maintaining a competitive trade-off among bit accuracy, payload capacity, and text quality compared with existing high-capacity baselines.
CLEF: Closed-Loop Error Feedback for Multi-Bit Watermarking in Short LLM-Generated Text
Jing Wang | Kejun Qian | Pengyu Xiong | Qiankun Zhang | Yi Yang | Jing Fan
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Jing Wang | Kejun Qian | Pengyu Xiong | Qiankun Zhang | Yi Yang | Jing Fan
Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
Multi-bit watermarking for large language models (LLMs) enables richer provenance information, but existing schemes remain unreliable for short texts because they rely on local or pre-specified allocation strategies. To address this limitation, we propose a Closed-Loop Error Feedback (CLEF) Multi-Bit Watermarking framework. By treating the LLM as a noisy channel, CLEF tracks the global feature state of generated tokens and dynamically measures its deviation from an ideal multidimensional target trajectory. The resulting dynamic error vector is then used to modulate the logits of candidate tokens via an inner-product scoring mechanism, biasing generation toward tokens that compensate for underrepresented payload dimensions. This closed-loop control enables robust multi-bit embedding with a simple, fully linear decoding process. Experiments on short-text generation show that CLEF improves bit extraction accuracy and complete message recovery rate over the evaluated multi-bit watermarking baselines. Furthermore, CLEF achieves higher bit extraction accuracy under different text perturbations while maintaining acceptable generation quality across downstream tasks such as text summarization and machine translation.
2025
Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling
Minghui Li | Hao Zhang | Yechao Zhang | Wei Wan | Shengshan Hu | Pei Xiaobing | Jing Wang
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Minghui Li | Hao Zhang | Yechao Zhang | Wei Wan | Shengshan Hu | Pei Xiaobing | Jing Wang
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and the poor transferability of black-box methods, we propose an activations-guided prompt injection attack framework. We first construct an Energy-based Model (EBM) using activations from a surrogate model to evaluate the quality of adversarial prompts. Guided by the trained EBM, we employ the token-level Markov Chain Monte Carlo (MCMC) sampling to adaptively optimize adversarial prompts, thereby enabling gradient-free black-box attacks. Experimental results demonstrate our superior cross-model transferability, achieving 49.6% attack success rate (ASR) across five mainstream LLMs and 34.6% improvement over human-crafted prompts, and maintaining 36.6% ASR on unseen task scenarios. Interpretability analysis reveals a correlation between activations and attack effectiveness, highlighting the critical role of semantic patterns in transferable vulnerability exploitation.
Search