Xuan Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xuan Xie has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Jiayang Song
University of Alberta, Edmonton, Canada
7 shared publications - Lei Ma
University of Tokyo, Tokyo, Japan
7 shared publications - Da Song
University of Alberta, Canada
3 shared publications - Yuheng Huang
University of Tokyo, Tokyo, Japan
3 shared publications - Zhehua Zhou
University of Alberta, Edmonton, Canada
3 shared publications - Felix Juefei-Xu
New York University, New York, NY, USA
2 shared publications
Latest Publications
- Open Access
- 20 August 2026
- Published by Elsevier in SSRN Electronic Journal
Test Generation based on Deep Learning: A Comprehensive Survey
Software testing is a core activity for software quality assurance. It has an indispensable role in checking the reliability, security, and performance of software systems. Among the various testing activities, Test-Case Generation (TCG) remains one of the most important yet challenging tasks. With an excellent record of success in Natural Language Processing (NLP), computer vision, and autonomous systems, Deep Learning (DL) has emerged as a transformative force in modern artificial intelligence, representing a potential paradigm shift for TCG. However, published work summarizing, classifying, and analyzing the process of Deep-Learning-based Test Generation (DLTG) remains scarce: To address this gap, this paper provides a comprehensive survey of the use of DL in TCG for software systems. We present the main phases of DLTG, identify publication trends, categorize input types, classify approaches, examine test-case types, and identify application scenarios. Currently available tools and experimental evaluations are also analyzed. We also summarize remaining key challenges and potential opportunities for future work.
- 20 August 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTest Generation based on Deep Learning: A Comprehensive Survey
Software testing is a core activity for software quality assurance. It has an indispensable role in checking the reliability, security, and performance of software systems. Among the various testing activities, Test-Case Generation (TCG) remains one of the most important yet challenging tasks. With an excellent record of success in Natural Language Processing (NLP), computer vision, and autonomous systems, Deep Learning (DL) has emerged as a transformative force in modern artificial intelligence, representing a potential paradigm shift for TCG. However, published work summarizing, classifying, and analyzing the process of Deep-Learning-based Test Generation (DLTG) remains scarce: To address this gap, this paper provides a comprehensive survey of the use of DL in TCG for software systems. We present the main phases of DLTG, identify publication trends, categorize input types, classify approaches, examine test-case types, and identify application scenarios. Currently available tools and experimental evaluations are also analyzed. We also summarize remaining key challenges and potential opportunities for future work.
- Open Access
AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks
Large language models (LLMs) remain vulnerable to jailbreak prompts that elicit harmful or policy-violating outputs, while many existing defenses rely on expensive fine-tuning, intrusive prompt rewriting, or external guardrails that add latency and can degrade helpfulness. We present AISA, a lightweight, single-pass defense that activates safety behaviors already latent inside the model rather than treating safety as an add-on. AISA first localizes intrinsic safety awareness via spatiotemporal analysis and shows that intent-discriminative signals are broadly encoded, with especially strong separability appearing in the scaled dot-product outputs of specific attention heads near the final structural tokens before generation. Using a compact set of automatically selected heads, AISA extracts an interpretable prompt-risk score with minimal overhead, achieving detector-level performance competitive with strong proprietary baselines on small (7B) models. AISA then performs logits-level steering: it modulates the decoding distribution in proportion to the inferred risk, ranging from normal generation for benign prompts to calibrated refusal for high-risk requests -- without changing model parameters, adding auxiliary modules, or requiring multi-pass inference. Extensive experiments spanning 13 datasets, 12 LLMs, and 14 baselines demonstrate that AISA improves robustness and transfer while preserving utility and reducing false refusals, enabling safer deployment even for weakly aligned or intentionally risky model variants.
Open AccessAISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks
Large language models (LLMs) remain vulnerable to jailbreak prompts that elicit harmful or policy-violating outputs, while many existing defenses rely on expensive fine-tuning, intrusive prompt rewriting, or external guardrails that add latency and can degrade helpfulness. We present AISA, a lightweight, single-pass defense that activates safety behaviors already latent inside the model rather than treating safety as an add-on. AISA first localizes intrinsic safety awareness via spatiotemporal analysis and shows that intent-discriminative signals are broadly encoded, with especially strong separability appearing in the scaled dot-product outputs of specific attention heads near the final structural tokens before generation. Using a compact set of automatically selected heads, AISA extracts an interpretable prompt-risk score with minimal overhead, achieving detector-level performance competitive with strong proprietary baselines on small (7B) models. AISA then performs logits-level steering: it modulates the decoding distribution in proportion to the inferred risk, ranging from normal generation for benign prompts to calibrated refusal for high-risk requests -- without changing model parameters, adding auxiliary modules, or requiring multi-pass inference. Extensive experiments spanning 13 datasets, 12 LLMs, and 14 baselines demonstrate that AISA improves robustness and transfer while preserving utility and reducing false refusals, enabling safer deployment even for weakly aligned or intentionally risky model variants.
- 7 February 2026
- Published by Springer Nature in Empirical Software Engineering
- Vol. 31 (3) , 67
Mosaic: model-based safety analysis for AI-enabled cyber physical system
- 7 February 2026
- Published by Springer Nature in Empirical Software Engineering
- Vol. 31 (3) , 67
Mosaic: model-based safety analysis for AI-enabled cyber physical system
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75, 2247-2259
Marvel: Effective AI-Enabled Cyber-Physical System Falsification Guided by Novelty Detection
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 75, 2247-2259
Marvel: Effective AI-Enabled Cyber-Physical System Falsification Guided by Novelty Detection
- 30 December 2025
- Published by Elsevier in Journal of Systems and Software
- Vol. 235
LeCov: Multi-level testing criteria for large language models
- 30 December 2025
- Published by Elsevier in Journal of Systems and Software
- Vol. 235
LeCov: Multi-level testing criteria for large language models
- 29 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (3) , 1626-1641
Online Safety Analysis for LLMs: A Benchmark, an Assessment, and a Path Forward
While Large Language Models (LLMs) have seen widespread applications across numerous fields, their limited interpretability poses concerns regarding their safe operations from multiple aspects, e.g., truthfulness and toxicity. Recent research has started developing quality assurance methods for LLMs, introducing techniques such as offline detectors or uncertainty estimation methods. However, these approaches mainly focus on post-generation analysis, leaving the online safety analysis for LLMs during the generation phase an unexplored area. To bridge this gap, we conduct in this work a comprehensive evaluation of the effectiveness of existing online safety analysis methods on LLMs. We begin with a pilot study that validates the feasibility of detecting unsafe outputs in the early generation process. Following this, we establish the first publicly available benchmark of online safety analysis for LLMs, including a broad spectrum of methods, models, tasks, datasets, and evaluation metrics. Utilizing this benchmark, we extensively analyze the performance of state-of-the-art online safety analysis methods on both open-source and closed-source LLMs. This analysis reveals the strengths and weaknesses of individual methods and offers valuable insights into selecting the most appropriate method based on specific application scenarios and task requirements. Furthermore, we also explore the potential of using hybridization methods, i.e., combining multiple methods to derive a collective safety conclusion, to enhance the efficacy of online safety analysis. Our findings indicate a promising direction for the development of trustworthy assurance methodologies for LLMs, facilitating their reliable deployments across diverse domains.
- 29 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (3) , 1626-1641
Online Safety Analysis for LLMs: A Benchmark, an Assessment, and a Path Forward
While Large Language Models (LLMs) have seen widespread applications across numerous fields, their limited interpretability poses concerns regarding their safe operations from multiple aspects, e.g., truthfulness and toxicity. Recent research has started developing quality assurance methods for LLMs, introducing techniques such as offline detectors or uncertainty estimation methods. However, these approaches mainly focus on post-generation analysis, leaving the online safety analysis for LLMs during the generation phase an unexplored area. To bridge this gap, we conduct in this work a comprehensive evaluation of the effectiveness of existing online safety analysis methods on LLMs. We begin with a pilot study that validates the feasibility of detecting unsafe outputs in the early generation process. Following this, we establish the first publicly available benchmark of online safety analysis for LLMs, including a broad spectrum of methods, models, tasks, datasets, and evaluation metrics. Utilizing this benchmark, we extensively analyze the performance of state-of-the-art online safety analysis methods on both open-source and closed-source LLMs. This analysis reveals the strengths and weaknesses of individual methods and offers valuable insights into selecting the most appropriate method based on specific application scenarios and task requirements. Furthermore, we also explore the potential of using hybridization methods, i.e., combining multiple methods to derive a collective safety conclusion, to enhance the efficacy of online safety analysis. Our findings indicate a promising direction for the development of trustworthy assurance methodologies for LLMs, facilitating their reliable deployments across diverse domains.
- 25 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 10678-10692
GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model
Safe reinforcement learning (SRL) aims to realize a safe learning process for deep reinforcement learning (DRL) algorithms by incorporating safety constraints. However, the efficacy of SRL approaches often relies on accurate function approximations, which are notably challenging to achieve in the early learning stages due to data insufficiency. To address this issue, we introduce, in this work, a novel generalizable safety enhancer (GenSafe) that can overcome the challenge of data insufficiency and enhance the performance of SRL approaches. Leveraging model order reduction techniques, we first propose an innovative method to construct a reduced order Markov decision process (ROMDP) as a low-dimensional approximator of the original safety constraints. Then, by solving the reformulated ROMDP-based constraints, GenSafe refines the actions of the agent to increase the possibility of constraint satisfaction. Essentially, GenSafe acts as an additional safety layer for SRL algorithms. We evaluate GenSafe on multiple SRL approaches and benchmark problems. The results demonstrate its capability to improve safety performance, especially in the early learning phases, while maintaining satisfactory task performance. Our proposed GenSafe not only offers a novel measure to augment existing SRL methods but also shows broad compatibility with various SRL algorithms, making it applicable to a wide range of systems and SRL problems.
- 25 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (6) , 10678-10692
GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model
Safe reinforcement learning (SRL) aims to realize a safe learning process for deep reinforcement learning (DRL) algorithms by incorporating safety constraints. However, the efficacy of SRL approaches often relies on accurate function approximations, which are notably challenging to achieve in the early learning stages due to data insufficiency. To address this issue, we introduce, in this work, a novel generalizable safety enhancer (GenSafe) that can overcome the challenge of data insufficiency and enhance the performance of SRL approaches. Leveraging model order reduction techniques, we first propose an innovative method to construct a reduced order Markov decision process (ROMDP) as a low-dimensional approximator of the original safety constraints. Then, by solving the reformulated ROMDP-based constraints, GenSafe refines the actions of the agent to increase the possibility of constraint satisfaction. Essentially, GenSafe acts as an additional safety layer for SRL algorithms. We evaluate GenSafe on multiple SRL approaches and benchmark problems. The results demonstrate its capability to improve safety performance, especially in the early learning phases, while maintaining satisfactory task performance. Our proposed GenSafe not only offers a novel measure to augment existing SRL methods but also shows broad compatibility with various SRL algorithms, making it applicable to a wide range of systems and SRL problems.
- 18 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 50 (7) , 1921-1948
LUNA: A Model-Based Universal Analysis Framework for Large Language Models
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.
- 18 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 50 (7) , 1921-1948
LUNA: A Model-Based Universal Analysis Framework for Large Language Models
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.
- Open Access
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 263-274
Towards Building AI-CPS with NVIDIA Isaac Sim: An Industrial Benchmark and Case Study for Robotics Manipulation
As a representative cyber-physical system (CPS), robotic manipulators have been widely adopted in various academic research and industrial processes, indicating their potential to act as a universal interface between the cyber and the physical worlds. Recent studies in robotics manipulation have started employing artificial intelligence (AI) approaches as controllers to achieve better adaptability and performance. However, the inherent challenge of explaining AI components introduces uncertainty and unreliability to these AI-enabled robotics systems, necessitating a reliable development platform for system design and performance assessment. As a foundational step towards building reliable AI-enabled robotics systems, in this paper, we propose a public benchmark for robotics manipulation. It leverages NVIDIA Omniverse Isaac Sim as the simulation platform, encompassing eight representative manipulation tasks and multiple AI software controllers. An extensive empirical evaluation is conducted to analyze the performance of AI controllers in solving robotics manipulation tasks, enabling a relatively thorough understanding of their effectiveness. To further demonstrate the applicability of our benchmark, we also developed the first falsification framework that is compatible with Isaac Sim. This framework bridges the gap between traditional falsification methods and modern physics engine-based simulations. The effectiveness of different optimization methods in falsifying AI-enabled robotics manipulation with physical simulators is also examined. Our work not only establishes a foundation for the design and development of AI-enabled robotics systems but also provides practical experience and guidance to practitioners in this field, promoting further research in this critical academic and industrial domain. The benchmarks, source code, and detailed evaluation results are available at https://sites.google.com/view/ai-cps-robotics-manipulation/home.
- 14 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 263-274
Open AccessTowards Building AI-CPS with NVIDIA Isaac Sim: An Industrial Benchmark and Case Study for Robotics Manipulation
As a representative cyber-physical system (CPS), robotic manipulators have been widely adopted in various academic research and industrial processes, indicating their potential to act as a universal interface between the cyber and the physical worlds. Recent studies in robotics manipulation have started employing artificial intelligence (AI) approaches as controllers to achieve better adaptability and performance. However, the inherent challenge of explaining AI components introduces uncertainty and unreliability to these AI-enabled robotics systems, necessitating a reliable development platform for system design and performance assessment. As a foundational step towards building reliable AI-enabled robotics systems, in this paper, we propose a public benchmark for robotics manipulation. It leverages NVIDIA Omniverse Isaac Sim as the simulation platform, encompassing eight representative manipulation tasks and multiple AI software controllers. An extensive empirical evaluation is conducted to analyze the performance of AI controllers in solving robotics manipulation tasks, enabling a relatively thorough understanding of their effectiveness. To further demonstrate the applicability of our benchmark, we also developed the first falsification framework that is compatible with Isaac Sim. This framework bridges the gap between traditional falsification methods and modern physics engine-based simulations. The effectiveness of different optimization methods in falsifying AI-enabled robotics manipulation with physical simulators is also examined. Our work not only establishes a foundation for the design and development of AI-enabled robotics systems but also provides practical experience and guidance to practitioners in this field, promoting further research in this critical academic and industrial domain. The benchmarks, source code, and detailed evaluation results are available at https://sites.google.com/view/ai-cps-robotics-manipulation/home.