Related papers: SoK: A Systematic Evaluation of Backdoor Trigger C…
Deep learning advances have enabled accurate six-degree-of-freedom (6DoF) object pose estimation, widely used in robotics, AR/VR, and autonomous systems. However, backdoor attacks pose significant security risks. While most research focuses…
Under a commonly-studied backdoor poisoning attack against classification models, an attacker adds a small trigger to a subset of the training data, such that the presence of this trigger at test time causes the classifier to always predict…
Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream…
Together with impressive advances touching every aspect of our society, AI technology based on Deep Neural Networks (DNN) is bringing increasing security concerns. While attacks operating at test time have monopolised the initial attention…
Deep learning models are increasingly used in mobile applications as critical components. Unlike the program bytecode whose vulnerabilities and threats have been widely-discussed, whether and how the deep learning models deployed in the…
Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack…
With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defender's capability to detect. We believe that answers to these…
Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs), enabling them to operate normally on clean inputs but manipulate predictions when specific trigger patterns occur. Currently, post-training backdoor…
Standard evaluations of backdoor attacks on text-to-image (T2I) models primarily measure trigger activation and visual fidelity. We challenge this paradigm, demonstrating that encoder-side poisoning induces persistent, trigger-free semantic…
Graph neural network (GNN) with a powerful representation capability has been widely applied to various areas, such as biological gene prediction, social recommendation, etc. Recent works have exposed that GNN is vulnerable to the backdoor…
Deep neural networks (DNNs) have achieved tremendous success in various applications including video action recognition, yet remain vulnerable to backdoor attacks (Trojans). The backdoor-compromised model will mis-classify to the target…
Backdoor attacks embed hidden functionalities in deep neural networks (DNN), triggering malicious behavior with specific inputs. Advanced defenses monitor anomalous DNN inferences to detect such attacks. However, concealed backdoors evade…
Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the same time, the attack power of an individual user is…
Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at training time. A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of the training data.…
Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the…
Although deep neural networks (DNNs) have achieved a great success in various computer vision tasks, it is recently found that they are vulnerable to adversarial attacks. In this paper, we focus on the so-called \textit{backdoor attack},…
Deep Learning (DL) has become a key technology that assists radio frequency (RF) signal classification applications, such as modulation classification. However, the DL models are vulnerable to adversarial machine learning threats, such as…
Machine learning models are increasingly present in our everyday lives; as a result, they become targets of adversarial attackers seeking to manipulate the systems we interact with. A well-known vulnerability is a backdoor introduced into a…
Machine unlearning has emerged as a key component in ensuring ``Right to be Forgotten'', enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set…
Deep learning models are susceptible to {\em backdoor attacks} involving malicious attackers perturbing a small subset of training data with a {\em trigger} to causes misclassifications. Various triggers have been used, including semantic…