In order to solve the grouting problem of tunnel lining vault cavity and local uncompacting, based on the project example of Qing-shiling tunnel and Yin-dongxia tunnel of Baoping Expressway, combined withthe existing...
详细信息
the large number of samples required in the fingerprint database creation phase leads to excessive time and labor costs. And too many sampling points in the fingerprint database will lead to too much computation when ...
详细信息
Battle commanders in modern war are facing new challenges such as massive information and short time windows. there is an urgent demand of intelligent assistant system to communicate withthe commanders and staff offi...
详细信息
Metamaterials introduce innovative possibilities for morphing wing design. this paper explores two methods of incorporating metamaterials into morphing wing design and applies a Multidisciplinary Design Optimization p...
详细信息
In recent years, Numerous stream clustering techniques have recently emerged. However these techniques do not utilize the valuable background knowledge provided by domain experts. Using knowledge in stream clustering ...
详细信息
Nowadays the growth of IoT is rapid and the MQTT protocol has become widely used in IoT communication. MQTT protocol does not come with strong security features except the username and password authentication. However...
详细信息
the boom in 3D printing has revolutionized manufacturing capabilities across all industries, offering unprecedented flexibility, adaptability and, last but not least, efficiency. However, the wide use of thermoplastic...
详细信息
Withthe development of IoT technology, a significant amount of time series data is continuously generated, and anomaly detection of this data is crucial. However, time series data in IoT is dynamic and heterogeneous,...
详细信息
Binary reverse engineering is crucial to gaining insights into the inner workings of a stripped binary. Yet, it is challenging to read the original semantics from a binary code snippet because of the unavailability of...
详细信息
ISBN:
(纸本)9798400704826
Binary reverse engineering is crucial to gaining insights into the inner workings of a stripped binary. Yet, it is challenging to read the original semantics from a binary code snippet because of the unavailability of high-level information in the source, such as function names, variable names, and types. Recent advancements in deep learning show the possibility of recovering such vanished information with a well-trained model from a pre-defined dataset. Albeit a static model's notable performance, it can hardly cope with an ever-increasing data stream (e.g., compiled binaries) by nature. the two viable approaches for ceaseless learning are retraining the whole dataset from scratch and fine-tuning a pre-trained model;however, retraining suffers from large computational overheads and fine-tuning from performance degradation (i.e., catastrophic forgetting). Lately, continual learning (CL) tackles the problem of handling incremental data in security domains (e.g., network intrusion detection, malware detection) using reasonable resources while maintaining performance in practice. In this paper, we focus on how CL assists in the improvement of a generative model that predicts a function symbol name from a series of machine instructions. To this end, we introduce BINADAPTER, a system that can infer function names from an incremental dataset without performance degradation from an original dataset by leveraging CL techniques. Our major finding shows that incremental tokens in the source (i.e., machine instructions) or the target (i.e., function names) largely affect the overall performance of a CL-enabled model. Accordingly, BINADAPTER adopts three built-in approaches: (1) inserting adapters in case of no incremental tokens in boththe source and target, (2) harnessing multilingual neural machine translation (M-NMT) and fine-tuning the source embeddings with (1) in case of incremental tokens in the source, and (3) fine-tuning target embeddings with (2) in case of incremen
While academic productivity in automated processes, such as artificial intelligence (AI), has increased fast, we currently need a complete knowledge of the implications of using these techniques in human resource mana...
详细信息
暂无评论