相关论文: Mitigating Backdoor Poisoning Attacks through the …

We propose a stealthy clean-label video backdoor attack against Deep Learning (DL)-based models aiming at detecting a particular class of spoofing attacks, namely video rebroadcast attacks. The injected backdoor does not affect spoofing…

Backdoor poisoning attacks behave counter-intuitively in high dimensions: stronger training triggers can help the defender. We study regularised generalised linear models on Gaussian-mixture data in the proportional regime ($p/n \to…

With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-following abilities and inability to distinguish the…

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that…

End-to-end deep learning exhibits unmatched performance for detecting malware, but such an achievement is reached by exploiting spurious correlations -- features with high relevance at inference time, but known to be useless through domain…

Although backdoor learning is an active research topic in the NLP domain, the literature lacks studies that systematically categorize and summarize backdoor attacks and defenses. To bridge the gap, we present a comprehensive and unifying…

Recent research has revealed that machine learning models have a tendency to leverage spurious correlations that exist in the training set but may not hold true in general circumstances. For instance, a sentiment classifier may erroneously…

Object detectors are vulnerable to backdoor attacks. In contrast to classifiers, detectors possess unique characteristics, architecturally and in task execution; often operating in challenging conditions, for instance, detecting traffic…

Deep Neural Network (DNN) models have vulnerabilities related to security concerns, with attackers usually employing complex hacking techniques to expose their structures. Data poisoning-enabled perturbation attacks are complex adversarial…

Deep neural networks (DNNs) are vulnerable to "backdoor" poisoning attacks, in which an adversary implants a secret trigger into an otherwise normally functioning model. Detection of backdoors in trained models without access to the…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering trigger patterns but fail to restore the correct semantic…

Relying only on unlabeled data, Self-supervised learning (SSL) can learn rich features in an economical and scalable way. As the drive-horse for building foundation models, SSL has received a lot of attention recently with wide…

Deep neural networks for image classification are well-known to be vulnerable to adversarial attacks. One such attack that has garnered recent attention is the adversarial backdoor attack, which has demonstrated the capability to perform…

State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…

Contrastive learning has become a leading self- supervised approach to representation learning across domains, including vision, multimodal settings, graphs, and federated learning. However, recent studies have shown that contrastive…

Model inversion attacks pose a significant privacy threat to machine learning models by reconstructing sensitive data from their outputs. While various defenses have been proposed to counteract these attacks, they often come at the cost of…

Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate exceptional performance, they face robustness challenges due to…

Backdoor attacks impose a new threat in Deep Neural Networks (DNNs), where a backdoor is inserted into the neural network by poisoning the training dataset, misclassifying inputs that contain the adversary trigger. The major challenge for…

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…