Changjia Zhu

Mr. Changjia Zhu


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2025
Verified
Conference Paper
Open access
PDF file
JXJunjie Xiong
Junjie Xiong
CZChangjia Zhu
Changjia Zhu
SLShuhang Lin
Shuhang Lin
CZChong Zhang
Chong Zhang
YZYongfeng Zhang
Yongfeng Zhang
LLLingyao Li
Lingyao Li
Junjie Xiong, Changjia Zhu, Shuhang Lin, Chong Zhang, Yongfeng Zhang, Yao Liu, Lingyao Li. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

12 September 2025 in arXiv
Verified
Preprint
Open access
PDF file
CZChangjia Zhu
Changjia Zhu
JXJunjie Xiong
Junjie Xiong
RMRenkai Ma
Renkai Ma
ZLZhicong Lu
Zhicong Lu
YLYao Liu
Yao Liu
LLLingyao Li
Lingyao Li
Peer review is the cornerstone of academic publishing, yet the process is increasingly strained by rising submission volumes, reviewer overload, and expertise mismatches. Large language models (LLMs) are now being used as "reviewer aids," raising concerns about their fairness, consistency, and robustness against indirect prompt injection attacks. This paper presents a systematic evaluation of LLMs as academic reviewers. Using a curated dataset of 1,441 papers from ICLR 2023 and NeurIPS 2022, we evaluate GPT-5-mini against human reviewers across ratings, strengths, and weaknesses. The evaluation employs structured prompting with reference paper calibration, topic modeling, and similarity analysis to compare review content. We further embed covert instructions into PDF submissions to assess LLMs' susceptibility to prompt injection. Our findings show that LLMs consistently inflate ratings for weaker papers while aligning more closely with human judgments on stronger contributions. Moreover, while overarching malicious prompts induce only minor shifts in topical focus, explicitly field-specific instructions successfully manipulate specific aspects of LLM-generated reviews. This study underscores both the promises and perils of integrating LLMs into peer review and points to the importance of designing safeguards that ensure integrity and trust in future review processes.

19 August 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
JXJunjie Xiong
Junjie Xiong
ZJZhengyuan Jiang
Zhengyuan Jiang
XXXiaoran Xu
Xiaoran Xu
CZChi Zhang
Chi Zhang
CZChangjia Zhu
Changjia Zhu
LLLingyao Li
Lingyao Li
Large Language Models (LLMs) have emerged as powerful tools that impact information integrity on social media platforms. This comprehensive review examines the dual role of LLMs in both facilitating and mitigating various information integrity challenges, including misinformation, disinformation, fake news, social bots, and privacy concerns. Through a systematic analysis of papers from academic databases, we identify key patterns in how LLMs influence social media ecosystems. Our findings reveal that while LLMs can enhance detection capabilities for malicious content and enable sophisticated defense mechanisms, they simultaneously pose risks by enabling the generation of highly convincing, deceptive content. We categorize and analyze the potential and challenges across different dimensions of information integrity, examining technical capabilities, ethical implications, and privacy concerns. The study demonstrates critical gaps in current approaches, particularly in cross-lingual detection, real-time monitoring, and privacy-preserving implementations. We conclude by proposing future research directions and recommendations for stakeholders to leverage LLMs while mitigating risks in social media information integrity.

22 May 2025 in arXiv
Verified
Preprint
Open access
PDF file
JXJunjie Xiong
Junjie Xiong
CZChangjia Zhu
Changjia Zhu
SLShuhang Lin
Shuhang Lin
CZChong Zhang
Chong Zhang
Yongfeng ZhangYongfeng Zhang
Yongfeng Zhang
LLLingyao Li
Lingyao Li
Large Language Models (LLMs) are increasingly equipped with capabilities of real-time web search and integrated with protocols like Model Context Protocol (MCP). This extension could introduce new security vulnerabilities. We present a systematic investigation of LLM vulnerabilities to hidden adversarial prompts through malicious font injection in external resources like webpages, where attackers manipulate code-to-glyph mapping to inject deceptive content which are invisible to users. We evaluate two critical attack scenarios: (1) "malicious content relay" and (2) "sensitive data leakage" through MCP-enabled tools. Our experiments reveal that indirect prompts with injected malicious font can bypass LLM safety mechanisms through external resources, achieving varying success rates based on data sensitivity and prompt design. Our research underscores the urgent need for enhanced security measures in LLM deployments when processing external content.