While deep learning techniques have achieved great success in modern digital products, researchers have shown that deep learning models are susceptible to Trojan attacks. In a Trojan attack, an adversary stealthily modifies a deep learning model such that the model will output a predefined label whenever a trigger is present in the input. In this paper, we present TrojanModel, a practical Trojan attack against Automatic Speech Recognition (ASR) systems. ASR systems aim to transcribe voice input into text, which is easier for subsequent downstream applications to process. We consider a practical attack scenario in which an adversary inserts a Trojan into the acoustic model of a target ASR system. Unlike existing work that uses noise-like triggers that will easily arouse user suspicion, the work in this paper focuses on the use of unsuspicious sounds as a trigger, e.g., a piece of music playing in the background. In addition, TrojanModel does not require the retraining of a target model. Experimental results show that TrojanModel can achieve high attack success rates with negligible effect on the target model’s performance. We also demonstrate that the attack is effective in an over-the-air attack scenario, where audio is played over a physical speaker and received by a microphone.

Network Intrusion Detection Systems (NIDS) often suffer from severe class imbalance, where minority attack types are underrepresented, leading to degraded detection performance. To address this challenge, we propose a novel augmentation framework that integrates Soft Nearest Neighbor Loss (SNNL) into Generative Adversarial Networks (GANs), including WGAN, CWGAN, and WGAN-GP. Unlike traditional oversampling methods (e.g., SMOTE, ADASYN), our approach improves feature-space alignment between real and synthetic samples, enhancing classifier generalization on rare classes. Experiments on NSL-KDD, CSE-CIC-IDS2017, and CSE-CIC-IDS2018 show that SNNL-augmented GANs consistently improve minority-class F1-scores without degrading overall accuracy or majority-class performance. UMAP visualizations confirm that SNNL produces more compact and class-consistent sample distributions. We also evaluate the computational overhead, finding the added cost moderate. These results demonstrate the effectiveness and practicality of SNNL as a general enhancement for GAN-based data augmentation in imbalanced NIDS tasks.