The expansion of Internet of Things (IoT) networks has enabled real-time data collection and automation across smart cities, healthcare, and agriculture, delivering greater convenience and efficiency; however, exposure to diverse threats has also increased. Machine learning-based Intrusion Detection Systems (IDSs) provide an effective means of defense, yet they require large volumes of data, and the use of raw IoT network data containing sensitive information introduces new privacy risks. This study proposes a novel privacy-preserving synthetic data generation model based on a tabular diffusion framework that incorporates Differential Privacy (DP). Among the three diffusion models (TabDDPM, TabSyn, and TabDiff), TabDiff with Utility-Preserving DP (UP-DP) achieved the best Synthetic Data Vault (SDV) Fidelity (0.98) and higher values on multiple statistical metrics, indicating improved utility. Furthermore, by employing the DisclosureProtection and attribute inference to infer and compare sensitive attributes on both real and synthetic datasets, we show that the proposed approach reduces privacy risk of the synthetic data. Additionally, a Membership Inference Attack (MIA) was also used for demonstration on models trained with both real and synthetic data. This approach decreases the risk of leaking patterns related to sensitive information, thereby enabling secure dataset sharing and analysis.
21 January 2026 in ACM Transactions on Software Engineering and Methodology
Side-channel attacks (SCAs) exploit power analysis to extract secret information. Researchers have employed this technique to disassemble software and retrieve cryptographic keys by examining power consumption or electromagnetic emissions. They utilized hardware or Hamming-based fluctuations measurement to profile or model the power leakage. Developers employ power modeling to comprehend software leakage, although manually profiling the power trace across various devices and architectures requires time and effort. This work proposes a custom deep learning (DL) method to model the power trace. The DL model was trained to analyze how each assembly instruction produces leakage based on its context with other instructions. The proposed method can predict the power trace with 0.9963 R² from unseen assembly instructions. This method automates device leakage testing and captures contextual and non-linear relationships to help developers understand the software behavior, significantly reducing the time and effort required for power modeling. The potential impact of this DL model on software security is that it can effectively mitigate the risk of SCAs, thus enhancing the overall security of software systems.
(1) Background: Side-channel attacks (SCAs) exploit unintended information leakage to compromise cryptographic security. In cyber-physical systems (CPSs), embedded systems are inherently constrained by limited resources, restricting the implementation of complex countermeasures. Traditional countermeasures, such as hiding techniques, attempt to obscure power consumption patterns; however, their effectiveness has been increasingly challenged. This study evaluates the vulnerability of dummy power traces against deep learning-based SCAs (DL-SCAs). (2) Methods: A power trace dataset was generated using a simulation environment based on Quick Emulator (QEMU) and GNU Debugger (GDB), integrating dummy traces to obfuscate execution signatures. DL models, including a Recurrent Neural Network (RNN), a Bidirectional RNN (Bi-RNN), and a Multi-Layer Perceptron (MLP), were used to evaluate classification performance. (3) Results: The models trained with dummy traces achieved high classification accuracy, with the MLP model reaching 97.81% accuracy and an F1-score of 97.77%. Despite the added complexity, DL models effectively distinguished real and dummy traces, highlighting limitations in existing hiding techniques. (4) Conclusions: These findings highlight the need for adaptive countermeasures against DL-SCAs. Future research should explore dynamic obfuscation techniques, adversarial training, and comprehensive evaluations of broader cryptographic algorithms. This study underscores the urgency of evolving security paradigms to defend against artificial intelligence-powered attacks.
(1) Background: Side-channel attacks (SCAs) exploit unintended information leakage to compromise cryptographic security. In cyber-physical systems (CPSs), embedded systems are inherently constrained by limited resources, which restricts the implementation of complex countermeasures. Traditional countermeasures such as hiding techniques attempt to obscure power consumption patterns, but deep learning models have challenged their effectiveness. This study evaluates the vulnerability of dummy power traces against deep learning-based SCAs. (2) Methods: A power trace dataset was generated using a QEMU and GDB-based simulation environment, integrating dummy traces to obfuscate execution signatures. Deep learning models—RNN, Bi-RNN, and MLP—were employed to assess classification accuracy. (3) Results: The models trained with dummy traces achieved higher classification accuracy, with the MLP model reaching 97.81% accuracy and an F1-score of 97.77%. Despite the added complexity, deep learning models effectively distinguished real and dummy traces, revealing limitations in existing hiding techniques. (4) Conclusions: These findings highlight the need for adaptive countermeasures against AI-driven SCAs. Future research should explore dynamic obfuscation techniques, adversarial training, and broader cryptographic algorithm evaluations. This study underscores the urgency of evolving security paradigms to counteract AI-powered attacks.