Related papers: A Wearables-Driven Attack on Examination Proctorin…

The widespread use of large language models (LLMs) is increasing the demand for methods that detect machine-generated text to prevent misuse. The goal of our study is to stress test the detectors' robustness to malicious attacks under…

Examining the authenticity of images has become increasingly important as manipulation tools become more accessible and advanced. Recent work has shown that while CNN-based image manipulation detectors can successfully identify…

We consider a multi-adversary version of the supervisory control problem for discrete-event systems, in which an adversary corrupts the observations available to the supervisor. The supervisor's goal is to enforce a specific language in…

Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training. Recent studies, however, have shown their vulnerability to adversarial attacks,…

A prompt injection attack aims to inject malicious instruction/data into the input of an LLM-Integrated Application such that it produces results as an attacker desires. Existing works are limited to case studies. As a result, the…

Deep neural networks used for human detection are highly vulnerable to adversarial manipulation, creating safety and privacy risks in real surveillance environments. Wearable attacks offer a realistic threat model, yet existing approaches…

Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable to adversarial examples. These adversarial inputs are…

Deep neural networks have empowered accurate device-free human activity recognition, which has wide applications. Deep models can extract robust features from various sensors and generalize well even in challenging situations such as…

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…

Examinations are a crucial part of the learning process, and academic institutions invest significant resources into maintaining their integrity by preventing cheating from students or facilitators. However, cheating has become rampant in…

As the pre-trained language models (PLMs) continue to grow, so do the hardware and data requirements for fine-tuning PLMs. Therefore, the researchers have come up with a lighter method called \textit{Prompt Learning}. However, during the…

With the rapid advancement of information technology, the complexity of applications continues to increase, and the cybersecurity challenges we face are also escalating. This paper aims to investigate the methods and practices of system…

Machine learning is used for inference and decision making in wearable sensor systems. However, recent studies have found that machine learning algorithms are easily fooled by the addition of adversarial perturbations to their inputs. What…

Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of detecting perturbed inputs. We show a barrier towards this goal. We prove a general hardness reduction between detection and…

Finding attackable sentences in an argument is the first step toward successful refutation in argumentation. We present a first large-scale analysis of sentence attackability in online arguments. We analyze driving reasons for attacks in…

Transfer learning is prevalent as a technique to efficiently generate new models (Student models) based on the knowledge transferred from a pre-trained model (Teacher model). However, Teacher models are often publicly available for sharing…

This study explores a handheld, battery-operated e-ink device displaying Google Scholar citation statistics. The StatCounter places academic metrics into the flow of daily life rather than a desktop context. The work draws on a…

Online proctoring has become a necessity in online teaching. Video-based crowd-sourced online proctoring solutions are being used, where an exam-taking student's video is monitored by third parties, leading to privacy concerns. In this…

Adversarial attacks pose significant challenges for detecting adversarial attacks at an early stage. We propose attack-agnostic detection on reinforcement learning-based interactive recommendation systems. We first craft adversarial…

Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering…