Related papers: Exploring Dynamic Properties of Backdoor Training …
The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.…
Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…
The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries…
Spiking Neural Networks (SNNs) are energy-efficient counterparts of Deep Neural Networks (DNNs) with high biological plausibility, as information is transmitted through temporal spiking patterns. The core element of an SNN is the spiking…
Backdoor attacks allow an attacker to embed functionality jeopardizing proper behavior of any algorithm, machine learning or not. This hidden functionality can remain inactive for normal use of the algorithm until activated by the attacker.…
In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor attack is an attack targeting the vulnerability of deep…
The ubiquity of deep neural networks (DNNs), cloud-based training, and transfer learning is giving rise to a new cybersecurity frontier in which unsecure DNNs have `structural malware' (i.e., compromised weights and activation pathways). In…
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can maliciously trigger model misclassifications by implanting a hidden backdoor during model training. This paper proposes a simple yet effective input-level…
Backdoor attacks insert malicious data into a training set so that, during inference time, it misclassifies inputs that have been patched with a backdoor trigger as the malware specified label. For backdoor attacks to bypass human…
With the growing popularity of artificial intelligence and machine learning, a wide spectrum of attacks against deep learning models have been proposed in the literature. Both the evasion attacks and the poisoning attacks attempt to utilize…
Combining the Information Bottleneck model with deep learning by replacing mutual information terms with deep neural nets has proved successful in areas ranging from generative modelling to interpreting deep neural networks. In this paper,…
Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malicious behaviors…
Deep anomaly detection on sequential data has garnered significant attention due to the wide application scenarios. However, deep learning-based models face a critical security threat - their vulnerability to backdoor attacks. In this…
Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…
Model Inversion (MI) attacks pose a significant threat to the privacy of Deep Neural Networks by recovering training data distribution from well-trained models. While existing defenses often rely on regularization techniques to reduce…
Sensor data-based recognition systems are widely used in various applications, such as gait-based authentication and human activity recognition (HAR). Modern wearable and smart devices feature various built-in Inertial Measurement Unit…
Information bottleneck is an information-theoretic principle of representation learning that aims to learn a maximally compressed representation that preserves as much information about labels as possible. Under this principle, two…
Backdoors and adversarial examples are the two primary threats currently faced by deep neural networks (DNNs). Both attacks attempt to hijack the model behaviors with unintended outputs by introducing (small) perturbations to the inputs.…
Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…
Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence. Existing methods often fail under strong detection or continuous fine-tuning, largely due to (1) cross-modal…