Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the blac...
Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier; the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA.
In the last decades, the area under cultivation of maize products has increased because of its essential role in the food cycle for humans, livestock, and poultry. Moreover, the diseases of plants impact food safety a...
详细信息
Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computervision, and biomedical signal processing. While the...
详细信息
Audio-visual semantic segmentation (AVSS) aims to segment and classify sounding objects in videos with acoustic cues. However, most approaches operate on the close-set assumption and only identify pre-defined categori...
详细信息
The propagation of SPPs in solid state systems is usually reciprocal, which means that a forward-traveling SPP wave can be easily backscattered by disorders. Since such backscattering is detrimental for SPP-based info...
详细信息
Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the blac...
详细信息
Understanding how the brain works is a base of cognitive info-communication. To this aim we focus on multiple target tracking (MTT) as a key task that involves two important cognitive factors, attention and memory. Hu...
详细信息
ISBN:
(数字)9798350378245
ISBN:
(纸本)9798350378252
Understanding how the brain works is a base of cognitive info-communication. To this aim we focus on multiple target tracking (MTT) as a key task that involves two important cognitive factors, attention and memory. Humans track multiple objects in their daily life while facing various challenges including occlusion and set-size. Eye movement research has shown that there are within and between subjects’ differences in scanpaths while performing MTT tasks. However, it is unclear if there is a winning scan pattern that would lead to a successful tracking of targets. To answer this question, we used dynamic time warping to compare the similarities between subjects’ scan patterns during an MTT task with different challenges. We studied the effect of set-size, occlusion, and trial response on the similarities. Then a mixed effect analysis was applied on the output to measure whether the findings were statistically significant. Results demonstrated that scan patterns were more similar when MTT task was performed correctly. It suggests that there is a common tracking strategy adopted by the viewers that leads to a correct response. Decoding this strategy has countless applications in the fields including human-computer interaction, brain-modeling and cognitive info-communication.
Mobile Edge Computing (MEC) provides users with low-latency, highly responsive services by deploying Edge Servers (ESs) near applications. MEC allows any edge-hosted application or service to be migrated between diffe...
详细信息
Contact-less or Device-less Human Activity Recognition (HAR) using IEEE 802.11 Wireless Local Area Network (WLAN) has garnered significant interest due to its ubiquitous coverage, convenience, and privacy compared to ...
Contact-less or Device-less Human Activity Recognition (HAR) using IEEE 802.11 Wireless Local Area Network (WLAN) has garnered significant interest due to its ubiquitous coverage, convenience, and privacy compared to wearable and vision-based approaches. However, maintaining the accuracy of HAR in varying environments, ranges, and time periods remains a challenge. This work proposes a robust scheme using threshold segmentation, auto-correlation function (ACF), and a lightweight fully connected neural network (FCNN), which can maintain the HAR accuracy across different environments without the need to retrain the model. The proposed scheme is also evaluated across different transceivers’ ranges to understand its deployment constraints. The results demonstrate that the proposed scheme delivers consistent performance across different environments, ranges, and days, achieving an average HAR accuracy of over 97.25% without retraining. This greatly reduces the deployment complexity and enhances its practicality.
Internet of things are increasingly being deployed over the cloud (also referred to as cloud of things) to provide a broader range of services. However, there are serious challenges of CoT in the data protection and s...
详细信息
暂无评论