相关论文: On Success and Simplicity: A Second Look at Transf…

Transferable adversarial attacks on point clouds remain challenging, as existing methods often rely on model-specific gradients or heuristics that limit generalization to unseen architectures. In this paper, we rethink adversarial…

Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data. We consider transferable poisoning attacks…

Machine learning systems deployed in distributed or federated environments are highly susceptible to adversarial manipulations, particularly availability attacks -adding imperceptible perturbations to training data, thereby rendering the…

Conventional text style transfer approaches focus on sentence-level style transfer without considering contextual information, and the style is described with attributes (e.g., formality). When applying style transfer in conversations such…

We design blackbox transfer-based targeted adversarial attacks for an environment where the attacker's source model and the target blackbox model may have disjoint label spaces and training datasets. This scenario significantly differs from…

Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the dependence on a large number of target domain data…

Transfer learning has emerged as a powerful technique for improving the performance of machine learning models on new domains where labeled training data may be scarce. In this approach a model trained for a source task, where plenty of…

Transfer Learning (TL) offers the potential to accelerate learning by transferring knowledge across tasks. However, it faces critical challenges such as negative transfer, domain adaptation and inefficiency in selecting solid source…

The widespread adoption of transfer learning has revolutionized machine learning by enabling efficient adaptation of pre-trained models to new domains. However, the reliability of these adaptations remains poorly understood, particularly…

Deep neural networks (DNNs) are highly susceptible to adversarial examples--subtle perturbations applied to inputs that are often imperceptible to humans yet lead to incorrect model predictions. In black-box scenarios, however, existing…

Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training processes. To better…

Two widely used techniques for training supervised machine learning models on small datasets are Active Learning and Transfer Learning. The former helps to optimally use a limited budget to label new data. The latter uses large pre-trained…

Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i.e., they remain adversarial even against other models. Although great efforts have been delved into the…

We present a general framework for matching with transferable utility (TU) that accommodates arbitrary heterogeneity without relying on the logit structure. The optimal assignment problem is characterized by tractable linear programming…

Moving Target Defense (MTD) has emerged as a key technique in various security applications as it takes away the attacker's ability to perform reconnaissance for exploiting a system's vulnerabilities. However, most of the existing research…

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…

With much longer optimization time than that of untargeted attacks notwithstanding, the transferability of targeted attacks is still far from satisfactory. Recent studies reveal that fine-tuning an existing adversarial example (AE) in…

Transfer learning has been proven effective when within-target labeled data is scarce. A lot of works have developed successful algorithms and empirically observed positive transfer effect that improves target generalization error using…

The generation of transferable adversarial perturbations typically involves training a generator to maximize embedding separation between clean and adversarial images at a single mid-layer of a source model. In this work, we build on this…

Many modern learning tasks require models that can take inputs of varying sizes. Consequently, dimension-independent architectures have been proposed for domains where the inputs are graphs, sets, and point clouds. Recent work on graph…