Related papers: Defending Black-box Skeleton-based Human Activity …
We present a new deep learning approach for real-time 3D human action recognition from skeletal data and apply it to develop a vision-based intelligent surveillance system. Given a skeleton sequence, we propose to encode skeleton poses and…
The growing body of literature on training-data reconstruction attacks raises significant concerns about deploying neural network classifiers trained on sensitive data. However, differentially private (DP) training (e.g. using DP-SGD) can…
This research provides a comprehensive overview of adversarial attacks on AI and ML models, exploring various attack types, techniques, and their potential harms. We also delve into the business implications, mitigation strategies, and…
Machine learning is a powerful tool enabling full automation of a huge number of tasks without explicit programming. Despite recent progress of machine learning in different domains, these models have shown vulnerabilities when they are…
Machine learning has seen tremendous advances in the past few years, which has lead to deep learning models being deployed in varied applications of day-to-day life. Attacks on such models using perturbations, particularly in real-life…
Backdoor unalignment attacks against Large Language Models (LLMs) enable the stealthy compromise of safety alignment using a hidden trigger while evading normal safety auditing. These attacks pose significant threats to the applications of…
To fluently collaborate with people, robots need the ability to recognize human activities accurately. Although modern robots are equipped with various sensors, robust human activity recognition (HAR) still remains a challenging task for…
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…
Adversarial training (AT) is a simple yet effective defense against adversarial attacks to image classification systems, which is based on augmenting the training set with attacks that maximize the loss. However, the effectiveness of AT as…
This paper presents RADAR-Robust Adversarial Detection via Adversarial Retraining-an approach designed to enhance the robustness of adversarial detectors against adaptive attacks, while maintaining classifier performance. An adaptive attack…
Backdoor attacks on deep learning represent a recent threat that has gained significant attention in the research community. Backdoor defenses are mainly based on backdoor inversion, which has been shown to be generic, model-agnostic, and…
Despite their promising performance across various natural language processing (NLP) tasks, current NLP systems are vulnerable to textual adversarial attacks. To defend against these attacks, most existing methods apply adversarial training…
Adversarial attacks have emerged as a major challenge to the trustworthy deployment of machine learning models, particularly in computer vision applications. These attacks have a varied level of potency and can be implemented in both white…
Defense strategies have been well studied to combat Byzantine attacks that aim to disrupt cooperative spectrum sensing by sending falsified versions of spectrum sensing data to a fusion center. However, existing studies usually assume…
Medical imaging AI systems such as disease classification and segmentation are increasingly inspired and transformed from computer vision based AI systems. Although an array of adversarial training and/or loss function based defense…
Human activity recognition (HAR) is essential for effective Human-Robot Collaboration (HRC), enabling robots to interpret and respond to human actions. This study evaluates the ability of a vision-based tactile sensor to classify 15…
With the rise in popularity of machine and deep learning models, there is an increased focus on their vulnerability to malicious inputs. These adversarial examples drift model predictions away from the original intent of the network and are…
Security-sensitive applications that rely on Deep Neural Networks (DNNs) are vulnerable to small perturbations that are crafted to generate Adversarial Examples(AEs). The AEs are imperceptible to humans and cause DNN to misclassify them.…
Human Action Recognition (HAR), one of the most important tasks in computer vision, has developed rapidly in the past decade and has a wide range of applications in health monitoring, intelligent surveillance, virtual reality, human…
Adversarially robust machine learning has received much recent attention. However, prior attacks and defenses for non-parametric classifiers have been developed in an ad-hoc or classifier-specific basis. In this work, we take a holistic…