Related papers: Diversity can be Transferred: Output Diversificati…

Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these…

Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled.…

Out-of-distribution detection (OOD) deals with anomalous input to neural networks. In the past, specialized methods have been proposed to reject predictions on anomalous input. Similarly, it was shown that feature extraction models in…

Deep neural networks are widely known to be vulnerable to adversarial examples, especially showing significantly poor performance on adversarial examples generated under the white-box setting. However, most white-box attack methods rely…

In generating adversarial examples, the conventional black-box attack methods rely on sufficient feedback from the to-be-attacked models by repeatedly querying until the attack is successful, which usually results in thousands of trials…

Subsampling from a large data set is useful in many supervised learning contexts to provide a global view of the data based on only a fraction of the observations. Diverse (or space-filling) subsampling is an appealing subsampling approach…

Given the severe vulnerability of Deep Neural Networks (DNNs) against adversarial examples, there is an urgent need for an effective adversarial attack to identify the deficiencies of DNNs in security-sensitive applications. As one of the…

A large body of recent work has investigated the phenomenon of evasion attacks using adversarial examples for deep learning systems, where the addition of norm-bounded perturbations to the test inputs leads to incorrect output…

Transferability, the ability of adversarial examples crafted for one model to deceive other models, is crucial for black-box attacks. Despite advancements in attack methods for semantic segmentation, transferability remains limited,…

Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources. Meanwhile, dataset distillation has emerged to synthesize a compact dataset that preserves critical…

Domain shifts are ubiquitous in machine learning, and can substantially degrade a model's performance when deployed to real-world data. To address this, distribution alignment methods aim to learn feature representations which are invariant…

Black-box adversarial attacks present a realistic threat to action recognition systems. Existing black-box attacks follow either a query-based approach where an attack is optimized by querying the target model, or a transfer-based approach…

Transfer learning has become a common practice for training deep learning models with limited labeled data in a target domain. On the other hand, deep models are vulnerable to adversarial attacks. Though transfer learning has been widely…

Deep learning has achieved tremendous success with independent and identically distributed (i.i.d.) data. However, the performance of neural networks often degenerates drastically when encountering out-of-distribution (OoD) data, i.e., when…

When machine learning (ML) models are supplied with data outside their training distribution, they are more likely to make inaccurate predictions; in a cyber-physical system (CPS), this could lead to catastrophic system failure. To mitigate…

Black-Box attacks on machine learning models occur when an attacker, despite having no access to the inner workings of a model, can successfully craft an attack by means of model theft. The attacker will train an own substitute model that…

Deep ensembles are capable of achieving state-of-the-art results in classification and out-of-distribution (OOD) detection. However, their effectiveness is limited due to the homogeneity of learned patterns within ensembles. To overcome…

Deep Learning has been shown to be particularly vulnerable to adversarial samples. To combat adversarial strategies, numerous defensive techniques have been proposed. Among these, a promising approach is to use randomness in order to make…

Adversarial examples are one critical security threat to various visual applications, where injected human-imperceptible perturbations can confuse the output.Generating transferable adversarial examples in the black-box setting is crucial…

Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks…