相关论文: Adversarial Attacks to Multi-Modal Models

Multimodal contrastive learning aims to train a general-purpose feature extractor, such as CLIP, on vast amounts of raw, unlabeled paired image-text data. This can greatly benefit various complex downstream tasks, including cross-modal…

The transferability of adversarial examples allows the deception on black-box models, and transfer-based targeted attacks have attracted a lot of interest due to their practical applicability. To maximize the transfer success rate,…

Transformer-based pre-trained models of code (PTMC) have been widely utilized and have achieved state-of-the-art performance in many mission-critical applications. However, they can be vulnerable to adversarial attacks through identifier…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Despite remarkable successes in unimodal learning tasks, backdoor attacks against cross-modal learning are still underexplored due to the limited generalization and inferior stealthiness when involving multiple modalities. Notably, since…

Adversarial examples tremendously threaten the availability and integrity of machine learning-based systems. While the feasibility of such attacks has been observed first in the domain of image processing, recent research shows that speech…

Almost all adversarial attacks are formulated to add an imperceptible perturbation to an image in order to fool a model. Here, we consider the opposite which is adversarial examples that can fool a human but not a model. A large enough and…

Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reverse-engineering the…

Recent approaches in machine learning often solve a task using a composition of multiple models or agentic architectures. When targeting a composed system with adversarial attacks, it might not be computationally or informationally feasible…

In recent years, there has been an explosive growth in multimodal learning. Image captioning, a classical multimodal task, has demonstrated promising applications and attracted extensive research attention. However, recent studies have…

Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks, however, generally assume that the victim model is…

Deep learning models are susceptible to adversarial attacks, where slight perturbations to input data lead to misclassification. Adversarial attacks become increasingly effective with access to information about the targeted classifier. In…

In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail. While these attack methods are…

The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversarial vulnerabilities. In general, existing adversarial…

Adversarial attacks refer to a set of methods that perturb the input to a classification model in order to fool the classifier. In this paper we apply different gradient based adversarial attack algorithms on five deep learning models…

Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabilities is especially difficult in the post-training setting,…

This is Btech thesis report on detection and purification of adverserially attacked images. A deep learning model is trained on certain training examples for various tasks such as classification, regression etc. By training, weights are…

Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning from a large-scale unlabeled dataset also exposes the model…

Deep Neural Networks are vulnerable to adversarial examples, i.e., carefully crafted input samples that can cause models to make incorrect predictions with high confidence. To mitigate these vulnerabilities, adversarial training and…

Adversarial attacks present a significant security risk to image recognition tasks. Defending against these attacks in a real-life setting can be compared to the way antivirus software works, with a key consideration being how well the…