English
Related papers

Related papers: Watermarking LLM Agent Trajectories

200 papers

Agentic systems for business process automation often require compliance with policies governing conditional updates to the system state. Evaluation of policy adherence in LLM-based agentic workflows is typically performed by comparing the…

Computation and Language · Computer Science 2026-05-15 Ella Rabinovich , David Boaz , Naama Zwerdling , Ateret Anaby-Tavor

With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern. While current watermarking techniques have the potential to identify the code LM…

Programming Languages · Computer Science 2025-09-18 Boyu Zhang , Ping He , Tianyu Du , Xuhong Zhang , Lei Yun , Kingsum Chow , Jianwei Yin

Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data…

Cryptography and Security · Computer Science 2025-07-29 Xinyue Cui , Johnny Tian-Zheng Wei , Swabha Swayamdipta , Robin Jia

Large language models (LLMs) can be trained or fine-tuned on data obtained without the owner's consent. Verifying whether a specific LLM was trained on particular data instances or an entire dataset is extremely challenging. Dataset…

Computation and Language · Computer Science 2025-10-07 Eyal German , Sagiv Antebi , Edan Habler , Asaf Shabtai , Yuval Elovici

Large Language Models (LLMs) are increasingly deployed as agents that orchestrate tasks and integrate external tools to execute complex workflows. We demonstrate that these interactive behaviors leave distinctive fingerprints in encrypted…

Cryptography and Security · Computer Science 2025-10-09 Yixiang Zhang , Xinhao Deng , Zhongyi Gu , Yihao Chen , Ke Xu , Qi Li , Jianping Wu

Large language models (LLMs) have demonstrated outstanding performance, making them valuable digital assets with significant commercial potential. Unfortunately, the LLM and its API are susceptible to intellectual property theft.…

Cryptography and Security · Computer Science 2024-07-25 Shuai Li , Kejiang Chen , Kunsheng Tang , Jie Zhang , Weiming Zhang , Nenghai Yu , Kai Zeng

Fine-tuning on agent-environment interaction trajectory data holds significant promise for surfacing generalized agent capabilities in open-source large language models (LLMs). In this work, we introduce AgentBank, by far the largest…

Computation and Language · Computer Science 2024-10-11 Yifan Song , Weimin Xiong , Xiutian Zhao , Dawei Zhu , Wenhao Wu , Ke Wang , Cheng Li , Wei Peng , Sujian Li

Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated…

Computation and Language · Computer Science 2026-05-29 Yukang Lin , Jiahao Shao , Shuoran Jiang , Wentao Zhu , Bingjie Lu , Xiangping Wu , Joanna Siebert , Qingcai Chen

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…

Machine Learning · Computer Science 2024-10-29 Xingchi Li , Guanxun Li , Xianyang Zhang

As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted…

Cryptography and Security · Computer Science 2026-05-15 William Lugoloobi , Samuelle Marro , Jabez Magomere , Joss Wright , Chris Russell

Evaluating the safety of LLM-based agents is increasingly important because risks in realistic deployments often emerge over multi-step interactions rather than isolated prompts or final responses. Existing trajectory-level benchmarks…

Artificial Intelligence · Computer Science 2026-05-14 Yu Li , Haoyu Luo , Yuejin Xie , Yuqian Fu , Zhonghao Yang , Shuai Shao , Qihan Ren , Wanying Qu , Yanwei Fu , Yujiu Yang , Jing Shao , Xia Hu , Dongrui Liu

Watermarking for large language models (LLMs) offers a promising approach to identifying AI-generated text. Existing approaches, however, either compromise the distribution of original generated text by LLMs or are limited to embedding…

Cryptography and Security · Computer Science 2025-06-09 Ya Jiang , Chuxiong Wu , Massieh Kordi Boroujeny , Brian Mark , Kai Zeng

As Large Language Models (LLMs) become increasingly sophisticated, they raise significant security concerns, including the creation of fake news and academic misuse. Most detectors for identifying model-generated text are limited by their…

Cryptography and Security · Computer Science 2024-10-10 Zhenyu Xu , Victor S. Sheng

Watermarking algorithms for large language models (LLMs) have attained high accuracy in detecting LLM-generated text. However, existing methods primarily focus on distinguishing fully watermarked text from non-watermarked text, overlooking…

Computation and Language · Computer Science 2025-02-25 Leyi Pan , Aiwei Liu , Yijian Lu , Zitian Gao , Yichen Di , Shiyu Huang , Lijie Wen , Irwin King , Philip S. Yu

Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to…

Cryptography and Security · Computer Science 2025-01-29 Aiwei Liu , Sheng Guan , Yiming Liu , Leyi Pan , Yifei Zhang , Liancheng Fang , Lijie Wen , Philip S. Yu , Xuming Hu

Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data, raising the possibility that these models may have been trained on proprietary datasets or the same benchmarks used for evaluation. This…

Machine Learning · Computer Science 2026-05-11 Pengrun Huang , Kamalika Chaudhuri , Yu-Xiang Wang

Large language models (LLMs) and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: (1) their effectiveness degrades…

Cryptography and Security · Computer Science 2026-04-02 Yanting Wang , Wei Zou , Runpeng Geng , Jinyuan Jia

The rise of LLMs has increased concerns over source tracing and copyright protection for AIGC, highlighting the need for advanced detection technologies. Passive detection methods usually face high false positives, while active watermarking…

Cryptography and Security · Computer Science 2026-04-03 Kahim Wong , Jicheng Zhou , Jiantao Zhou , Yain-Whar Si

The increasing use of Large Language Models (LLMs) for generating highly coherent and contextually relevant text introduces new risks, including misuse for unethical purposes such as disinformation or academic dishonesty. To address these…

Computation and Language · Computer Science 2024-10-16 Zhenyu Xu , Kun Zhang , Victor S. Sheng

Large Language Model (LLM)-based agents are increasingly employed to automate complex software engineering tasks, such as program repair and issue resolution. These agents operate by autonomously generating natural language thoughts,…

Software Engineering · Computer Science 2025-10-09 Islem Bouzenia , Michael Pradel