相关论文: DeDe: Detecting Backdoor Samples for SSL Encoders …

With the success of deep learning algorithms in various domains, studying adversarial attacks to secure deep models in real world applications has become an important research topic. Backdoor attacks are a form of adversarial attacks on…

Deep Learning backdoor attacks have a threat model similar to traditional cyber attacks. Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks. In this paper,…

Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model. The modified training samples…

Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on CLIP models by poisoning only 0.01\% of the training…

With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing…

Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few training samples. The attacked model behaves normally on benign…

Pre-trained encoders are general-purpose feature extractors that can be used for many downstream tasks. Recent progress in self-supervised learning can pre-train highly effective encoders using a large volume of unlabeled data, leading to…

Masked image modeling (MIM) revolutionizes self-supervised learning (SSL) for image pre-training. In contrast to previous dominating self-supervised methods, i.e., contrastive learning, MIM attains state-of-the-art performance by masking…

Dense retrieval systems have been widely used in various NLP applications. However, their vulnerabilities to potential attacks have been underexplored. This paper investigates a novel attack scenario where the attackers aim to mislead the…

Classifiers in supervised learning have various security and privacy issues, e.g., 1) data poisoning attacks, backdoor attacks, and adversarial examples on the security side as well as 2) inference attacks and the right to be forgotten for…

While multimodal contrastive learning methods (e.g., CLIP) can achieve impressive zero-shot classification performance, recent research has revealed that these methods are vulnerable to backdoor attacks. To defend against backdoor attacks…

This paper finds that contrastive learning can produce superior sentence embeddings for pre-trained models but is also vulnerable to backdoor attacks. We present the first backdoor attack framework, BadCSE, for state-of-the-art sentence…

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…

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…

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…

Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on…

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by…

Recent studies have verified that semi-supervised learning (SSL) is vulnerable to data poisoning backdoor attacks. Even a tiny fraction of contaminated training data is sufficient for adversaries to manipulate up to 90\% of the test outputs…

The monitoring of individuals/objects has become increasingly possible in recent years due to the convenience of integrated cameras in many devices. Due to the important moments or activities of people captured by these devices, it has made…

This paper highlights vulnerabilities of deep learning-driven semantic communications to backdoor (Trojan) attacks. Semantic communications aims to convey a desired meaning while transferring information from a transmitter to its receiver.…