Related papers: Mutual-modality Adversarial Attack with Semantic P…

Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we…

Machine learning models are known to be vulnerable to adversarial attacks, but traditional attacks have mostly focused on single-modalities. With the rise of large multi-modal models (LMMs) like CLIP, which combine vision and language…

Adversarial examples generated from surrogate models often possess the ability to deceive other black-box models, a property known as transferability. Recent research has focused on enhancing adversarial transferability, with input…

Adversarial transferability refers to the capacity of adversarial examples generated on the surrogate model to deceive alternate, unexposed victim models. This property eliminates the need for direct access to the victim model during an…

Learning joint embedding space for various modalities is of vital importance for multimodal fusion. Mainstream modality fusion approaches fail to achieve this goal, leaving a modality gap which heavily affects cross-modal fusion. In this…

While the transferability property of adversarial examples allows the adversary to perform black-box attacks (i.e., the attacker has no knowledge about the target model), the transfer-based adversarial attacks have gained great attention.…

Adversarial purification is a successful defense mechanism against adversarial attacks without requiring knowledge of the form of the incoming attack. Generally, adversarial purification aims to remove the adversarial perturbations…

Recent studies have revealed the vulnerability of pre-trained language models to adversarial attacks. Existing adversarial defense techniques attempt to reconstruct adversarial examples within feature or text spaces. However, these methods…

Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks. Typically, such attacks either involve frequent queries to the target model or rely on surrogate models closely mirroring the target model…

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Recent studies have shown that adversarial examples hand-crafted on one white-box model can be used to attack other black-box models. Such cross-model transferability makes it feasible to perform black-box attacks, which has raised security…

Deep neural networks are vulnerable to adversarial examples that mislead the models with imperceptible perturbations. Though adversarial attacks have achieved incredible success rates in the white-box setting, most existing adversaries…

Evasion attacks are a threat to machine learning models, where adversaries attempt to affect classifiers by injecting malicious samples. An alarming side-effect of evasion attacks is their ability to transfer among different models: this…

Transferable attacks generate adversarial examples on surrogate models to fool unknown victim models, posing real-world threats and growing research interest. Despite focusing on flat losses for transferable adversarial examples, recent…

Though CNNs have achieved the state-of-the-art performance on various vision tasks, they are vulnerable to adversarial examples --- crafted by adding human-imperceptible perturbations to clean images. However, most of the existing…

Adversarial attacks are carried out to reveal the vulnerability of deep neural networks. Textual adversarial attacking is challenging because text is discrete and a small perturbation can bring significant change to the original input.…

Converting different modalities into generalized text, which then serves as input prompts for large language models (LLMs), is a common approach for aligning multimodal models, particularly when pairwise data is limited. Text-centric…

In targeted adversarial attacks on vision models, the selection of the target label is a critical yet often overlooked determinant of attack success. This target label corresponds to the class that the attacker aims to force the model to…

Transfer-based adversarial example is one of the most important classes of black-box attacks. However, there is a trade-off between transferability and imperceptibility of the adversarial perturbation. Prior work in this direction often…

Adversarial attacks have threatened the application of deep neural networks in security-sensitive scenarios. Most existing black-box attacks fool the target model by interacting with it many times and producing global perturbations.…