University of Liverpool TACPS Lab

Publications

Evidence, methods and open questions.

Browse the lab’s publication record by year or search across authors, titles and venues.

78 publications

2026

  1. Boxuan Wang, Zhuoyun Li, Xinmiao Huang, Xiaowei Huang, and Yi Dong (2026). Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), Volume 1: Long Papers, pp. 39514–39530.
  2. Jinwei Hu, Xinmiao Huang, Youcheng Sun, Yi Dong, and Xiaowei Huang (2026). Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage. ACL 2026, Volume 1: Long Papers, pp. 5979–5996. Outstanding Paper Award.
  3. Xinmiao Huang, Qisong He, Zhenglin Huang, Boxuan Wang, Zhuoyun Li, Guangliang Cheng, Yi Dong, and Xiaowei Huang (2026). Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models. International Conference on Learning Representations (ICLR 2026).
  4. Aharon Azulay, Jan Dubiński, Zhuoyun Li, Atharv Mittal, and Yossi Gandelsman (2026). Jailbreaking Vision-Language Models Through the Visual Modality. Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), PMLR 306, pp. 4636–4670.
  5. Qisong He, Xinmiao Huang, Jinwei Hu, Zhuoyun Li, Yi Dong, Changshun Wu, and Xiaowei Huang (2026). Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026).
  6. Tianxiao Li, Zhenglin Huang, Haiquan Wen, Yiwei He, Xinze Li, Bingyu Zhu, Wuhui Duan, Congang Chen, Zeyu Fu, Yi Dong, Baoyuan Wu, Xiangtai Li, and Guangliang Cheng (2026). Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2026), pp. 30299–30311.
  7. Xi Yang, Chang Liu, Zhenglin Huang, Haoran Li, Weiming Zhang, Jian Weng, and Yangqiu Song (2026). Steering LLM Viewpoints through Fabricated Evidence Injection. Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), pp. 9310–9326.
  8. Jinwei Hu, Yi Dong, Youcheng Sun, and Xiaowei Huang (2026). Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), pp. 29477–29485.
  9. Jinwei Hu, Shiyuan Meng, Yi Dong, and Xiaowei Huang (2026). DDSA: Dual-Domain Strategic Attack for Spatial-Temporal Efficiency in Adversarial Robustness Testing. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2026), pp. 19842–19846.
  10. Zhen Chen, Yi Zhang, Xiangyu Yin, Chengxuan Qin, Xingyu Zhao, Xiaowei Huang, and Wenjie Ruan (2026). Fragile by Design: On the Limits of Adversarial Defenses in Personalized DreamBooth Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(45), pp. 38304–38312.
  11. Yi Zhang, Zhen Chen, Chih-Hong Cheng, Wenjie Ruan, Xiaowei Huang, Dezong Zhao, David Flynn, Siddartha Khastgir, and Xingyu Zhao (2026). Trustworthy text-to-image diffusion models: a timely and focused survey. Information Fusion, 133, 104264.
  12. Jinwei Hu, Yi Dong, Zhengtao Ding, and Xiaowei Huang (2026). Enhancing robustness of LLM-driven multi-agent systems through randomized smoothing. Chinese Journal of Aeronautics, 39(7), 103779.
  13. Dayou Chen, Yi Yang, Jinwei Hu, Matthew Kasoar, Rossella Arcucci, and Sibo Cheng (2026). Explainable global wildfire prediction model using graph neural networks. Geodata and AI, 7, 100052.
  14. Kewei Zhu, Yanze Xin, Jinwei Hu, Xiaoyuan Cheng, Yiming Yang, and Sibo Cheng (2026). Spatiotemporal system forecasting with irregular time steps via masked autoencoder. Physica D: Nonlinear Phenomena, 492, 135189.

2025

  1. Jinwei Hu, Zhenglin Huang, Xiangyu Yin, Wenjie Ruan, Guangliang Cheng, Yi Dong, and Xiaowei Huang (2025). FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model. Advances in Neural Information Processing Systems 38 (NeurIPS 2025).
  2. Zhenglin Huang, Jinwei Hu, Xiangtai Li, Yiwei He, Xingyu Zhao, Bei Peng, Baoyuan Wu, Xiaowei Huang, and Guangliang Cheng (2025). SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), pp. 28831–28841.
  3. Tianxiao Li, Zhenglin Huang, Haiquan Wen, Yiwei He, Shuchang Lyu, Baoyuan Wu, and Guangliang Cheng (2025). RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection. ACM International Conference on Multimedia (ACM MM 2025), pp. 11746–11755.
  4. Yi Zhang, Yuhang Chen, Zhen Chen, Wenjie Ruan, Xiaowei Huang, Siddartha Khastgir, and Xingyu Zhao (2025). Adversarial Training for Probabilistic Robustness. IEEE/CVF International Conference on Computer Vision (ICCV 2025), pp. 1675–1685.
  5. Shuang Ao, Yi Dong, Jinwei Hu, and Sarvapali D. Ramchurn (2025). Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs. Transactions of the Association for Computational Linguistics, 13, pp. 1474–1487.
  6. Yi Dong, Ronghui Mu, Yanghao Zhang, Siqi Sun, Tianle Zhang, Changshun Wu, Gaojie Jin, Yi Qi, Jinwei Hu, Jie Meng, Saddek Bensalem, and Xiaowei Huang (2025). Safeguarding large language models: a survey. Artificial Intelligence Review, 58, 382.
  7. Jinwei Hu, Zezhi Tang, Xin Jin, Benyuan Zhang, Yi Dong, and Xiaowei Huang (2025). Hierarchical Testing With Rabbit Optimization for Industrial Cyber-Physical Systems. IEEE Transactions on Industrial Cyber-Physical Systems, 3, pp. 472–484.
  8. Luo Cheng, Hanwei Zhang, Qisong He, Wei Huang, Renjue Li, Xiaowei Huang, Holger Hermanns, and Lijun Zhang (2025). Eidos revisited: Expanding Efficient, imperceptible adversarial attacks on 3D point clouds. Journal of Systems Architecture, 169, 103595.

2024

  1. Zhen Chen, Yi Zhang, Fu Wang, Xingyu Zhao, Xiaowei Huang, and Wenjie Ruan (2024). TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models. Advances in Neural Information Processing Systems 37 (NeurIPS 2024).
  2. Yi Dong, Ronghui Mu, Gaojie Jin, Yi Qi, Jinwei Hu, Xingyu Zhao, Jie Meng, Wenjie Ruan, and Xiaowei Huang (2024). Position: Building Guardrails for Large Language Models Requires Systematic Design. Proceedings of the 41st International Conference on Machine Learning (ICML 2024), PMLR 235, pp. 11375–11394.
  3. Hanwei Zhang, Luo Cheng, Qisong He, Wei Huang, Renjue Li, Ronan Sicre, Xiaowei Huang, Holger Hermanns, and Lijun Zhang (2024). Eidos: Efficient, Imperceptible Adversarial 3D Point Clouds. International Symposium on Dependable Software Engineering: Theories, Tools, and Applications (SETTA 2024), LNCS 15469, pp. 310–326.
  4. Zhen Chen, Fu Wang, Ronghui Mu, Peipei Xu, Xiaowei Huang, and Wenjie Ruan (2024). NRAT: Towards Adversarial Training with Inherent Label Noise. Machine Learning, 113, pp. 3589–3610.
  5. Jinwei Hu, Kewei Zhu, Sibo Cheng, Nina M. Kovalchuk, Alfred Soulsby, Mark J. H. Simmons, Omar K. Matar, and Rossella Arcucci (2024). Explainable AI models for predicting drop coalescence in microfluidics device. Chemical Engineering Journal, 481, 148465.
  6. Chuandong Xie, Jinwei Hu, George Vasdravellis, Xiantie Wang, and Sibo Cheng (2024). Explainable AI model for predicting equivalent viscous damping in dual frame–wall resilient system. Journal of Building Engineering, 96, 110564.
  7. Nausheen Basha, Rossella Arcucci, Panagiota Angeli, Charitos Anastasiou, Thomas Abadie, César Quilodrán Casas, Jianhua Chen, Sibo Cheng, Loïc Chagot, Federico Galvanin, Claire E. Heaney, Fria Hossein, Jinwei Hu, Nina Kovalchuk, Maria Kalli, Lyes Kahouadji, Morgan Kerhouant, Alessio Lavino, Fuyue Liang, Konstantia Nathanael, Luca Magri, Paola Lettieri, Massimiliano Materazzi, Matteo Erigo, Paula Pico, Christopher C. Pain, Mosayeb Shams, Mark Simmons, Tullio Traverso, Juan Pablo Valdes, Zef Wolffs, Kewei Zhu, Yilin Zhuang, and Omar K. Matar (2024). Machine learning and physics-driven modelling and simulation of multiphase systems. International Journal of Multiphase Flow, 179, 104936.
  8. Dong Y., Wang Y., Gama M., Mustafa M. A., Deconinck G., Huang X. (2024). Privacy-preserving Distributed Learning for Residential Short-term Load Forecasting. IEEE Internet of Things Journal (IF: 10.6).
  9. Dong, Y., Zhao, X., Wang, S., & Huang, X. (2024). Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems. IEEE Robotics and Automation Letters 2024.

2023

  1. Huang, X., Ruan, W., Huang, W., Jin, G., Dong, Y., Wu, C., ... & Mustafa, M. A. (2023). A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation. arXiv preprint arXiv:2305.11391.
  2. Xu, P., Wang, F., Ruan, W., Zhang, C., & Huang, X. (2023, June). Sora: Scalable Black-Box Reachability Analyser on Neural Networks. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1-5). IEEE.
  3. Huang, W., Zhao, X., Banks, A., Cox, V., & Huang, X. (2023). Hierarchical Distribution-Aware Testing of Deep Learning. ACM Transactions on Software Engineering and Methodology 2023.
  4. Cai, K., Lu, C. X., & Huang, X. (2023). Uncertainty Estimation for 3D Dense Prediction via Cross-Point Embeddings. IEEE Robotics and Automation Letters, 8(5), 2558-2565.
  5. Qi, Y., Zhao, X., & Huang, X. (2023). Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT. arXiv preprint arXiv:2304.01246.
  6. Qi, Y., Dong, Y., Zhao, X., & Huang, X. (2023). Stpa for learning-enabled systems: A survey and a new method. ITSC2023.
  7. Huang, X., Jin, G., & Ruan, W. (2023). Machine Learning Safety. Springer.
  8. Dong, Y., Li, Z., Zhao, X., Ding, Z., & Huang, X. (2023). Decentralised and Cooperative Control of Multi-Robot Systems through Distributed Optimisation. AAMAS'23.
  9. Wu, D., Jin, G., Yu, H., Yi, X., & Huang, X. (2023). Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff. arXiv preprint arXiv:2301.09522.
  10. Jin, G., Yi, X., Wu, D., Mu, R., & Huang, X. (2023). Randomized adversarial training via taylor expansion. CVPR2023.
  11. Huang, W., Zhao, X., Jin, G., & Huang, X. (2023). SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability. ICCV2023.

2022

  1. Dong, Y., Huang, W., Bharti, V., Cox, V., Banks, A., Wang S., Zhao X., Schewe S. & Huang, X. (2022). Reliability Assessment and Safety Arguments for Machine Learning Components in Assuring Learning-Enabled Autonomous Systems. ACM Transactions on Embedded Computing Systems.
  2. Dong, Y., Chen, Y., Zhao, X., & Huang, X. (2022). Short-term Load Forecasting with Distributed Long Short-Term Memory. 2023 IEEE ISGT North America.
  3. Huang, X., Ruan, W., Tang, Q., & Zhao, X. (2022). Bridging formal methods and machine learning with global optimisation. In International Conference on Formal Engineering Methods (pp. 1-19). Springer, Cham.
  4. Huang, X., Peng, B., & Zhao, X. (2022). Dependable learning-enabled multiagent systems. AI Communications, 1-14.
  5. Huang, W., Zhao, X., Banks, A., Cox, V., & Huang, X. (2022). Hierarchical Distribution-Aware Testing of Deep Learning. arXiv preprint arXiv:2205.08589.
  8. Cai, K., Lu, C. X., & Huang, X. (2022). STUN: Self-Teaching Uncertainty Estimation for Place Recognition. IROS2022.
  9. Qi, Y., Conmy, P. R., Huang, W., Zhao, X., & Huang, X. (2022). A Hierarchical HAZOP-Like Safety Analysis for Learning-Enabled Systems. in AISafety Workshop at IJCAI2022.
  10. Jin, G., Yi, X., Huang, W., Schewe, S., & Huang, X. Enhancing Adversarial Training with Second-Order Statistics of Weights. CVPR 2022.
  11. Alshareef, A., Berthier, N., Schewe, S., & Huang, X. Quantifying the Importance of Latent Features in Neural Networks. In SafeAI’22 Workshop at AAAI’22.
  12. Jin, G., Yi, X., Yang, P., Zhang, L., Schewe, S., & Huang, X. (2022). Weight Expansion: A New Perspective on Dropout and Generalization. arXiv preprint arXiv:2201.09209.
  13. Jin, G., Yi, X., & Huang, X. (2022). Neuronal Correlation: a Central Concept in Neural Network. arXiv preprint arXiv:2201.09069.

2021

  1. Huang, W., Zhao, X. & Huang, X. (2021) Embedding and extraction of knowledge in tree ensemble classifiers. Machine Learning.
  2. Zhao, X., Huang, W., Banks, A., Cox, V., Flynn, D., Schewe, S., and Huang, X. (2021a). Assessing the reliability of deep learning classifiers through robustness evaluation andoperational profiles. In AISafety’21 Workshop at IJCAI’21.
  3. Huang, W., Sun, Y., Zhao, X., Sharp, J., Ruan, W., Meng, J. and Huang, X., 2021. Coverage Guided Testing for Recurrent Neural Networks , IEEE Tran. On Reliability.
  4. Zhao, X., Huang, W., Huang, X., Robu, V. and Flynn, D., 2021. BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations , UAI2021.
  6. Zhao, X., Huang, W., Schewe, S., Dong, Y. and Huang, X., 2021. Detecting Operational Adversarial Examples for Reliable Deep Learning , DSN'21 (fast abstract).

2020

  1. Jin, G., Yi, X., Zhang, L., Zhang, L., Schewe, S. and Huang, X., 2020. How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks? . Advances in Neural Information Processing Systems, 33.
  2. Meng, Y., Meng, W., Gao, D., Zhao, Y., Yang, X., Huang, X. and Zheng, Y., 2020, August. Regression of Instance Boundary by Aggregated CNN and GCN . In European Conference on Computer Vision (pp. 190-207). Springer, Cham.
  3. Sun, Y., Chockler, H., Huang, X. and Kroening, D., 2020, August. Explaining Image Classifiers using Statistical Fault Localization . In European Conference on Computer Vision (pp. 391-406). Springer, Cham.
  4. Huang, X., Kroening, D., Ruan, W., Sharp, J., Sun, Y., Thamo, E., Wu, M. and Yi, X., 2020. A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability . Computer Science Review, 37, p.100270.
  5. Sun, Y., Zhou, Y., Maskell, S., Sharp, J. and Huang, X., 2020, May. Reliability validation of learning enabled vehicle tracking . In 2020 IEEE International Conference on Robotics and Automation (ICRA) (pp. 9390-9396). IEEE.
  6. Li, R., Li, J., Huang, C.C., Yang, P., Huang, X., Zhang, L., Xue, B. and Hermanns, H., 2020, November. PRODeep: a platform for robustness verification of deep neural networks . In Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (pp. 1630-1634).
  7. Meng, Y., Wei, M., Gao, D., Zhao, Y., Yang, X., Huang, X. and Zheng, Y., 2020, October. CNN-GCN aggregation enabled boundary regression for biomedical image segmentation . In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 352-362). Springer, Cham.
  8. Zhao, X., Banks, A., Sharp, J., Robu, V., Flynn, D., Fisher, M. and Huang, X., 2020, September. A safety framework for critical systems utilising deep neural networks . In International Conference on Computer Safety, Reliability, and Security (pp. 244-259). Springer, Cham.
  9. Huang, W., Zhou, Y., Sun, Y., Sharp, J., Maskell, S. and Huang, X., 2020. Practical Verification of Neural Network Enabled State Estimation System for Robotics .

2019

  1. Sun, Y., Huang, X., Kroening, D., Sharp, J., Hill, M. and Ashmore, R., 2019. Structural test coverage criteria for deep neural networks . ACM Transactions on Embedded Computing Systems (TECS), 18(5s), pp.1-23.
  2. Zhao, X., Osborne, M., Lantair, J., Robu, V., Flynn, D., Huang, X., Fisher, M., Papacchini, F. and Ferrando, A., 2019, September. Towards integrating formal verification of autonomous robots with battery prognostics and health management . In International Conference on Software Engineering and Formal Methods (pp. 105-124). Springer, Cham.
  3. Ruan, W., Wu, M., Sun, Y., Huang, X., Kroening, D. and Kwiatkowska, M., 2019, August. Global robustness evaluation of deep neural networks with provable guarantees for the hamming distance . IJCAI.
  4. Wu, M., Louw, T., Lahijanian, M., Ruan, W., Huang, X., Merat, N. and Kwiatkowska, M., 2019, November. Gaze-based intention anticipation over driving manoeuvres in semi-autonomous vehicles . In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 6210-6216). IEEE.
  5. Sun, Y., Huang, X., Kroening, D., Sharp, J., Hill, M. and Ashmore, R., 2019, May. DeepConcolic: Testing and debugging deep neural networks . In 2019 IEEE/ACM 41st International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) (pp. 111-114). IEEE.

2018

  1. Sun, Y., Wu, M., Ruan, W., Huang, X., Kwiatkowska, M. and Kroening, D., 2018, September. Concolic testing for deep neural networks . In Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering (pp. 109-119).
  2. Wicker, M., Huang, X. and Kwiatkowska, M., 2018, April. Feature-guided black-box safety testing of deep neural networks . In International Conference on Tools and Algorithms for the Construction and Analysis of Systems (pp. 408-426). Springer, Cham.
  3. Ruan, W., Huang, X. and Kwiatkowska, M., 2018. Reachability analysis of deep neural networks with provable guarantees . arXiv preprint arXiv:1805.02242.