Derui Zhu

Mr. Derui Zhu

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
1 January 2024
Verified
Conference Paper
Open access
PDF file
QLQing Li
Qing Li
JGJiahui Geng
Jiahui Geng
CLChenyang Lyu
Chenyang Lyu
DZDerui Zhu
Derui Zhu
MPMaxim Panov
Maxim Panov
FKFakhri Karray
Fakhri Karray
Qing Li, Jiahui Geng, Chenyang Lyu, Derui Zhu, Maxim Panov, Fakhri Karray. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

18 June 2024 in IEEE Transactions on Software Engineering
Verified
Journal Article
Closed access
DSDa Song
Da Song
XXXuan Xie
Xuan Xie
JSJiayang Song
Jiayang Song
DZDerui Zhu
Derui Zhu
YHYuheng Huang
Yuheng Huang
LMLei Ma
Lei Ma
Over the past decade, Artificial Intelligence (AI) has had great success recently and is being used in a wide range of academic and industrial fields. More recently, Large Language Models (LLMs) have made rapid advancements that have propelled AI to a new level, enabling and empowering even more diverse applications and industrial domains with intelligence, particularly in areas like software engineering and natural language processing. Nevertheless, a number of emerging trustworthiness concerns and issues exhibited in LLMs, e.g., robustness and hallucination, have already recently received much attention, without properly solving which the widespread adoption of LLMs could be greatly hindered in practice. The distinctive characteristics of LLMs, such as the self-attention mechanism, extremely large neural network scale, and autoregressive generation usage contexts, differ from classic AI software based on Convolutional Neural Networks and Recurrent Neural Networks and present new challenges for quality analysis. Up to the present, it still lacks universal and systematic analysis techniques for LLMs despite the urgent industrial demand across diverse domains. Towards bridging such a gap, in this paper, we initiate an early exploratory study and propose a universal analysis framework for LLMs, named LUNA , which is designed to be general and extensible and enables versatile analysis of LLMs from multiple quality perspectives in a human-interpretable manner. In particular, we first leverage the data from desired trustworthiness perspectives to construct an abstract model as an auxiliary analysis asset and proxy, which is empowered by various abstract model construction methods built-in LUNA . To assess the quality of the abstract model, we collect and define a number of evaluation metrics, aiming at both the abstract model level and the semantics level. Then, the semantics, which is the degree of satisfaction of the LLM w.r.t. the trustworthiness perspective, is bound to and enriches the abstract model with semantics, which enables more detailed analysis applications for diverse purposes, e.g., abnormal behavior detection. To better understand the potential usefulness of our analysis framework LUNA, we conduct a large-scale evaluation, the results of which demonstrate that 1) the abstract model has the potential to distinguish normal and abnormal behavior in LLM, 2) LUNA is effective for the real-world analysis of LLMs in practice, and the hyperparameter settings influence the performance, 3) different evaluation metrics are in different correlations with the analysis performance. In order to encourage further studies in the quality assurance of LLMs, we made all of the code and more detailed experimental results data available on the supplementary website of this paper https://sites.google.com/view/llm-luna.

8 February 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Open access
DZDerui Zhu
Derui Zhu
JCJinfu Chen
Jinfu Chen
XZXuebing Zhou
Xuebing Zhou
WSWeiyi Shang
Weiyi Shang
AHAhmed E. Hassan
Ahmed E. Hassan
JGJens Grossklags
Jens Grossklags
Vertical federated learning (VFL) is an increasingly popular, yet understudied, collaborative learning technique. In VFL, features and labels are distributed among different participants allowing for various innovative applications in business domains, e.g., online marketing. When deploying VFL, training data (labels and features) from each participant ought to be protected; however, very few studies have investigated the vulnerability of data protection in the VFL training stage. In this paper, we propose a posterior-difference-based data attack, VFLRecon , reconstructing labels and features to examine this problem. Our experiments show that standard VFL is highly vulnerable to serious privacy threats, with reconstruction achieving up to 92% label accuracy and 0.05 feature MSE, compared to our baseline with 55% label accuracy and 0.19 feature MSE. Even worse, this privacy risk remains during standard operations (e.g., encrypted aggregation) that appear to be safe. We also systematically analyze data leakage risks in the VFL training stage across diverse data modalities (i.e., tabular data and images), different training frameworks (i.e., with or without encryption techniques), and a wide range of training hyperparameters. To mitigate this risk, we design a novel defense mechanism, VFLDefender , dedicated to obfuscating the correlation between bottom model changes and labels (features) during training. The experimental results demonstrate that VFLDefender prevents reconstruction attacks during standard encryption operations (around 17% more effective than standard encryption operations).

1 January 2024
Verified
Conference Paper
Open access
PDF file
DZDerui Zhu
Derui Zhu
DCDingfan Chen
Dingfan Chen
QLQing Li
Qing Li
ZCZongxiong Chen
Zongxiong Chen
LMLei Ma
Lei Ma
MFMario Fritz
Mario Fritz
Derui Zhu, Dingfan Chen, Qing Li, Zongxiong Chen, Lei Ma, Jens Grossklags, Mario Fritz. Findings of the Association for Computational Linguistics: NAACL 2024. 2024.

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
QLQing Li
Qing Li
JGJiahui Geng
Jiahui Geng
DZDerui Zhu
Derui Zhu
ZCZongxiong Chen
Zongxiong Chen
KSKun Song
Kun Song
FKFakhri Karray
Fakhri Karray
Warning: This paper contains offensive content that may disturb some readers. Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the integration of images significantly shifts the model's internal activations during the forward pass, diverging from those triggered by textual input. Moreover, the safety alignments of LLMs embedded within VLMs are not sufficiently robust to handle the activations discrepancies, making the models vulnerable to even the simplest jailbreaking attacks. To address this issue, we propose an internal activation revision approach that efficiently revises activations during generation, steering the model toward safer outputs. Our framework incorporates revisions at both the layer and head levels, offering control over the model's generation at varying levels of granularity. In addition, we explore three strategies for constructing positive and negative samples and two approaches for extracting revision vectors, resulting in different variants of our method. Comprehensive experiments demonstrate that the internal activation revision method significantly improves the safety of widely used VLMs, reducing attack success rates by an average of 48.94%, 34.34%, 43.92%, and 52.98% on SafeBench, Safe-Unsafe, Unsafe, and MM-SafetyBench, respectively, while minimally impacting model helpfulness.

11 February 2023 in Empirical Software Engineering
Verified
Journal Article
Closed access
PDF file
AAAmin Eslami Abyane
Amin Eslami Abyane
DZDerui Zhu
Derui Zhu
RSRoberto Souza
Roberto Souza
LMLei Ma
Lei Ma
HHHadi Hemmati
Hadi Hemmati