Zhaofen Wu, Hanrong Zhang, Fulin Lin, Wujiang Xu, Xinran Xu, Yankai Chen, Henry Peng Zou, Shaowen Chen, Weizhi Zhang, Xue Liu, Philip S. Yu, Hongwei Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Fault diagnosis plays a significant role in the intelligent maintenance of industrial processes. Although there are numerous deep learning methods designed for fault diagnosis, certain challenges remain difficult to address in real-world industrial scenarios. These challenges include ensuring high- precision fault detection while maintaining industrial privacy in the presence of sensitive data, as well as achieving accurate detection when fault samples are limited. This paper proposes an industrial data generation framework using diffusion and flow- based models. The proposed approach learns the distribution of the original data to generate synthetic samples with similar characteristics, effectively resolving the dual challenges of data sensitivity and scarcity. Experiments on the Tennessee Eastman dataset demonstrate that our approach outperforms existing methods in fault diagnosis performance.

Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patches or visible noise, which are vulnerable to human inspection. This paper proposes an imperceptible and effective backdoor attack against self-supervised models. We first find that existing imperceptible triggers designed for supervised learning are less effective in compromising self-supervised models. We then identify this ineffectiveness is attributed to the overlap in distributions between the backdoor and augmented samples used in SSL. Building on this insight, we design an attack using optimized triggers disentangled with the augmented transformation in the SSL, while remaining imperceptible to human vision. Experiments on five datasets and six SSL algorithms demonstrate our attack is highly effective and stealthy. It also has strong resistance to existing backdoor defenses. Our code can be found at https://github.com/Zhang-Henry/INACTIVE.

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature does not comprehensively evaluate attacks and defenses against LLM-based agents. To address this, we introduce Agent Security Bench (ASB), a comprehensive framework designed to formalize, benchmark, and evaluate the attacks and defenses of LLM-based agents, including 10 scenarios (e.g., e-commerce, autonomous driving, finance), 10 agents targeting the scenarios, over 400 tools, 27 different types of attack/defense methods, and 7 evaluation metrics. Based on ASB, we benchmark 10 prompt injection attacks, a memory poisoning attack, a novel Plan-of-Thought backdoor attack, 4 mixed attacks, and 11 corresponding defenses across 13 LLM backbones. Our benchmark results reveal critical vulnerabilities in different stages of agent operation, including system prompt, user prompt handling, tool usage, and memory retrieval, with the highest average attack success rate of 84.30\%, but limited effectiveness shown in current defenses, unveiling important works to be done in terms of agent security for the community. We also introduce a new metric to evaluate the agents' capability to balance utility and security. Our code can be found at https://github.com/agiresearch/ASB.

Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge. However, limited research exists for imbalanced and long-tailed data. Extracting discriminative features from few-shot fault data is challenging, and adding new fault classes often demands costly model retraining. Moreover, incremental training of existing methods risks catastrophic forgetting, and severe class imbalance can bias the model's decisions toward normal classes. To tackle these issues, we introduce a supervised contrastive knowledge distillation for class incremental fault diagnosis (SCLIFD) framework proposing supervised contrastive knowledge distillation for improved representation learning capability and less forgetting, a novel prioritized exemplar selection method for sample replay to alleviate catastrophic forgetting, and the random forest classifier to address the class imbalance. Extensive experimentation on simulated and real-world industrial datasets across various imbalance ratios demonstrates the superiority of SCLIFD over existing approaches.

Fault diagnosis is crucial in monitoring machines within industrial processes. With the increasing complexity of working conditions and demand for safety during production, diverse diagnosis methods are required, and an integrated fault diagnosis system capable of handling multiple tasks is highly desired. However, the diagnosis subtasks are often studied separately, and the current methods still need improvement for such a generalized system. To address this issue, we propose the generalized out-of-distribution fault diagnosis (GOOFD) framework to integrate diagnosis subtasks. Additionally, a unified fault diagnosis method based on internal contrastive learning and Mahalanobis distance is put forward to underpin the proposed generalized framework. The method involves feature extraction through internal contrastive learning and outlier recognition based on the Mahalanobis distance. Our proposed method can be applied to multiple fault diagnosis tasks and achieve better performance than the existing single-task methods. Experiments are conducted on benchmark and practical process datasets, indicating the effectiveness of the proposed framework.

Compared with traditional multivariate statistical techniques, deep neural networks have been frequently used for single-mode fault diagnosis and have shown promising results. However, in the real world, a complex industrial process may have several modes and fewer fault samples than normal. Although several multivariate statistical techniques focus on multimode fault diagnosis, those methods usually identify modes and then locally diagnose faults while ignoring relative information across modes and data imbalance problems. In this paper, a deep learning-based method combining Multi-gate Mixture-of-Experts (MMOE) and Synthetic Minority Over-sampling Technique (SMOTE) is proposed to address multimode imbalance fault diagnosis. Specifically, MMOE can identify modes and diagnose faults in each mode simultaneously. Furthermore, it investigates the common information of multiple modes by sharing network parameters. Moreover, SMOTE can address the fault imbalance problem by over-sampling minority fault samples. The experiment results show the performance improvements of multimode imbalance fault diagnosis using MMOE-SMOTE on the Tennessee Eastman (TE) Chemical benchmark process.