Related papers: T$_k$ML-AP: Adversarial Attacks to Top-$k$ Multi-L…
Adversarial training (AT) with imperfect supervision is significant but receives limited attention. To push AT towards more practical scenarios, we explore a brand new yet challenging setting, i.e., AT with complementary labels (CLs), which…
Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a…
The goal in extreme multi-label classification is to learn a classifier which can assign a small subset of relevant labels to an instance from an extremely large set of target labels. Datasets in extreme classification exhibit a long tail…
The rapid growth of deep learning has brought about powerful models that can handle various tasks, like identifying images and understanding language. However, adversarial attacks, an unnoticed alteration, can deceive models, leading to…
Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…
Multimodal Large Language Models (MLLMs) have achieved remarkable performance across vision-language tasks. Recent advancements allow these models to process multiple images as inputs. However, the vulnerabilities of multi-image MLLMs…
Advanced Persistent Threats (APTs) pose a significant challenge in cybersecurity due to their stealthy and long-term nature. Modern supervised learning methods require extensive labeled data, which is often scarce in real-world…
Extreme Multilabel Text Classification (XMTC) is a text classification problem in which, (i) the output space is extremely large, (ii) each data point may have multiple positive labels, and (iii) the data follows a strongly imbalanced…
Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models (VLMs). This part of the training pipeline is critical for supplying…
Existing textual adversarial attacks usually utilize the gradient or prediction confidence to generate adversarial examples, making it hard to be deployed in real-world applications. To this end, we consider a rarely investigated but more…
Generating high-quality textual adversarial examples is critical for investigating the pitfalls of natural language processing (NLP) models and further promoting their robustness. Existing attacks are usually realized through word-level or…
Adversarial examples are perturbed inputs which can cause a serious threat for machine learning models. Finding these perturbations is such a hard task that we can only use the iterative methods to traverse. For computational efficiency,…
A human's attention can intuitively adapt to corrupted areas of an image by recalling a similar uncorrupted image they have previously seen. This observation motivates us to improve the attention of adversarial images by considering their…
Deep neural networks are capable of state-of-the-art performance in many classification tasks. However, they are known to be vulnerable to adversarial attacks -- small perturbations to the input that lead to a change in classification. We…
Semantic overlap among land-cover categories, highly imbalanced label distributions, and complex inter-class co-occurrence patterns constitute significant challenges for multi-label remote-sensing image retrieval. In this article,…
Sufficient supervised information is crucial for any machine learning models to boost performance. However, labeling data is expensive and sometimes difficult to obtain. Active learning is an approach to acquire annotations for data from a…
Existing adversarial learning approaches mostly use class labels to generate adversarial samples that lead to incorrect predictions, which are then used to augment the training of the model for improved robustness. While some recent works…
Paucity of large curated hand-labeled training data for every domain-of-interest forms a major bottleneck in the deployment of machine learning models in computer vision and other fields. Recent work (Data Programming) has shown how distant…
Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt gradients or confidence scores to calculate word importance ranking and generate adversarial examples. However, this…
Advanced Persistent Threats (APTs) present a considerable challenge to cybersecurity due to their stealthy, long-duration nature. Traditional supervised learning methods typically require large amounts of labeled data, which is often scarce…