Zhenhua Wang

Dr. Zhenhua Wang

NUDT
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
21 April 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ZWZhenhua Wang
Zhenhua Wang
WXWei Xie
Wei Xie
BWBaosheng Wang
Baosheng Wang
JTJing Tao
Jing Tao
EWEnze Wang
Enze Wang
Cyber-physical systems (CPSs) are next-generation intelligent systems that integrate computing, communication, and control. Malicious attacks on CPSs can lead to both property damage and casualties. Therefore, it is worth surveying CPS security by reviewing and analyzing the latest high-quality related works. In this paper, we provide an overview of the CPS security studies from the last five years and select 142 related works from A- or B-level conferences/journals recommended by the China Computer Federation (CCF). First, we review the main contents of the selected papers and classify them into 24 topics. Then, we analyze hotspots and trends of CPS security technologies in three dimensions: (1) architecture layers (perception, network, and application); (2) application scenarios (smart grids, health care, smart transportation, smart homes, and general grids); and (3) MADC (Measure, Attack, Defense, and Control) types. Finally, we also perform a statistical analysis in terms of paper publication times, author institutes, countries, and sponsors to show the current worldwide CPS security research situation.

5 May 2025 in Sensors
Verified
Journal Article
Open access
PDF file
EWEnze Wang
Enze Wang
WXWei Xie
Wei Xie
SLShuhuan Li
Shuhuan Li
RLRunhao Liu
Runhao Liu
YZYuan Zhou
Yuan Zhou
BWBaosheng Wang
Baosheng Wang
Broken access control vulnerabilities pose significant security risks to the protected web interfaces of IoT devices, enabling adversaries to gain unauthorized access to sensitive configurations and even use them as stepping stones for attacking the intranet. Despite its ranking as the first in the latest OWASP Top 10, there remains a lack of effective methodologies to detect these vulnerabilities systematically. We present ACBreaker, a novel methodology powered by a large language model (LLM), to effectively identify broken access control vulnerabilities in the protected web interfaces of IoT devices. Our methodology consists of three stages. The initial stage transforms firmware code that exceeds the LLM context window into semantically intact code snippets. The second stage involves using an LLM to extract device-specific information from firmware code. The final stage integrates this information into the mutation-based fuzzer to improve fuzzing effectiveness and employ differential analysis to identify vulnerabilities. We evaluated ACBreaker across 11 IoT devices, analyzing 1,274,646 lines of code and discovering 39 previously unknown vulnerabilities. We further analyzed these vulnerabilities, categorizing them into three types that contribute to protected interface evasion, and provided mitigation suggestions. These vulnerabilities were responsibly disclosed to vendors, with CVE IDs assigned to those in six IoT devices.

17 August 2025 in Electronics
Verified
Journal Article
Open access
PDF file
ZWZhenhua Wang
Zhenhua Wang
WXWei Xie
Wei Xie
SMShuoyoucheng Ma
Shuoyoucheng Ma
EWEnze Wang
Enze Wang
BWBaosheng Wang
Baosheng Wang
Large Language Models (LLMs) have demonstrated effectiveness across various tasks, yet they remain susceptible to malicious exploitation. Adversaries can circumvent LLMs’ safety constraints (“jail”) through carefully engineered “jailbreaking” prompts. Researchers have developed various jailbreak techniques leveraging optimization, obfuscation, and persuasive tactics to assess LLM security. However, these approaches frame LLMs as passive targets of manipulation, overlooking their capacity for active reasoning. In this work, we introduce Persu-Agent, a novel jailbreak framework grounded in Greenwald’s Cognitive Response Theory. Unlike previous approaches that focus primarily on prompt design, we target the LLM’s internal reasoning process. Persu-Agent prompts the model to generate its justifications for harmful queries, effectively persuading itself. Experiments on advanced open-source and commercial LLMs show that Persu-Agent achieves an average jailbreak success rate of 84%, outperforming existing SOTA methods. Our findings offer new insights into the cognitive tendencies of LLMs and contribute to developing more secure and robust LLMs.

6 December 2025 in Electronics
Verified
Journal Article
Open access
PDF file
ZWZhenhua Wang
Zhenhua Wang
WXWei Xie
Wei Xie
SMShuoyoucheng Ma
Shuoyoucheng Ma
EWEnze Wang
Enze Wang
BWBaosheng Wang
Baosheng Wang
Large Language Models (LLMs) can adopt various roles through prompt guidance, enabled by pretraining on diverse corpora and instruction-following alignment. Safety alignment mechanisms attempt to define a helpful, honest, and harmless assistant to guide their behavior. However, specific role settings can bypass these safeguards, inducing LLMs to respond to harmful queries. In this study, we identify the role settings that lead LLMs to generate such harmful responses, which contribute to more reliable LLMs. We design an automated jailbreak framework, RoleBreaker, that optimizes role-play prompts with representation analysis and adaptive search. Experiments on 7 open-source LLMs show that RoleBreaker achieves an average jailbreak success rate of 87.3% with 4.0 attempts, outperforming SOTA methods. Furthermore, by summarizing the jailbreak experiences and applying them to closed-source commercial models (GPT-4.1, GLM-4, Gemini-2.0), we achieve an average jailbreak success rate of 84.3% with 4.3 attempts. These results reveal vulnerabilities in current alignment mechanisms and demonstrate the transferability of our approach.

4 November 2021
Verified
Book Chapter
Closed access
PDF file
ZWZhenhua Wang
Zhenhua Wang
WXWei Xie
Wei Xie
JTJing Tao
Jing Tao
YTYong Tang
Yong Tang
EWEnze Wang
Enze Wang