相关论文: A Wearables-Driven Attack on Examination Proctorin…

Machine learning models are famously vulnerable to adversarial attacks: small ad-hoc perturbations of the data that can catastrophically alter the model predictions. While a large literature has studied the case of test-time attacks on…

Influence estimation tools -- such as memorization scores -- are widely used to understand model behavior, attribute training data, and inform dataset curation. However, recent applications in data valuation and responsible machine learning…

One of the oft-cited qualities sought after in a potential future engineering employee is an analytical mind that is "continually examining things." In one sense this examination is discouraged in an instructional laboratory employing…

Security attacks are growing in an exponential manner and their impact on existing systems is seriously high and can lead to dangerous consequences. However, in order to reduce the effect of these attacks, penetration tests are highly…

The onset of the COVID-19 pandemic changed the landscape of education and led to increased usage of remote proctoring tools that are designed to monitor students when they take assessments outside the classroom. While prior work has…

Modern automated surveillance techniques are heavily reliant on deep learning methods. Despite the superior performance, these learning systems are inherently vulnerable to adversarial attacks - maliciously crafted inputs that are designed…

With the rapid advancement of AI models, their deployment across diverse tasks has become increasingly widespread. A notable emerging application is leveraging AI models to assist in reviewing scientific papers. However, recent reports have…

Adversarial attacks insert small, imperceptible perturbations to input samples that cause large, undesired changes to the output of deep learning models. Despite extensive research on generating adversarial attacks and building defense…

A good amount of research has explored the use of wearables for educational or learning purposes. We have now reached a point when much literature can be found on that topic, but few attempts have been made to make sense of that literature…

In this research, a literature in human-computer interaction is reviewed and the technology aspect of human computer interaction related with digital academic supportive devices is also analyzed. According to all these concerns,…

The focus of this paper is on wearable technologies which are increasingly being employed in the medical field. From smart watches to smart glasses, from electronic textile to data gloves; several gadgets are playing important roles in…

An ever-growing body of work has demonstrated the rich information content available in eye movements for user modelling, e.g. for predicting users' activities, cognitive processes, or even personality traits. We show that state-of-the-art…

Proactive monitoring of one's health could avoid serious diseases as well as better maintain the individual's well-being. In today's IoT world, there has been numerous wearable technological devices to monitor/measure different health…

Purpose of the research: In the biometric community, visible human characteristics are popular and viable for verification and identification on mobile devices. However, imposters are able to spoof such characteristics by creating fake and…

Turing test was originally proposed to examine whether machine's behavior is indistinguishable from a human. The most popular and practical Turing test is CAPTCHA, which is to discriminate algorithm from human by offering recognition-alike…

Modern language models have enabled the development of agentic systems that achieve strong performance on reasoning-intensive tasks. Unfortunately, this has come with a security cost; these systems are vulnerable to prompt injection, a…

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively, prompt hacking), in…

Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks…

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly…

Intelligent robots rely on object detection models to perceive the environment. Following advances in deep learning security it has been revealed that object detection models are vulnerable to adversarial attacks. However, prior research…