Related papers: Defuse: Harnessing Unrestricted Adversarial Exampl…

With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing…

Adequate sampling space coverage is the keystone to effectively train trustworthy Machine Learning models. Unfortunately, real data do carry several inherent risks due to the many potential biases they exhibit when gathered without a proper…

A machine learning model, under the influence of observed or unobserved confounders in the training data, can learn spurious correlations and fail to generalize when deployed. For image classifiers, augmenting a training dataset using…

Datasets often contain biases which unfairly disadvantage certain groups, and classifiers trained on such datasets can inherit these biases. In this paper, we provide a mathematical formulation of how this bias can arise. We do so by…

Testing of deep learning models is challenging due to the excessive number and complexity of computations involved. As a result, test data selection is performed manually and in an ad hoc way. This raises the question of how we can…

Localization of unknown faults in industrial systems is a difficult task for data-driven diagnosis methods. The classification performance of many machine learning methods relies on the quality of training data. Unknown faults, for example…

Global Navigation Satellite Systems (GNSS) are vital for reliable urban positioning. However, multipath and non-line-of-sight reception often introduce large measurement errors that degrade accuracy. Learning-based methods for predicting…

With the proliferation of multi-core hardware, parallel programs have become ubiquitous. These programs have their own type of bugs known as concurrency bugs and among them, data race bugs have been mostly in the focus of researchers over…

Memorization in over-parameterized neural networks could severely hurt generalization in the presence of mislabeled examples. However, mislabeled examples are hard to avoid in extremely large datasets collected with weak supervision. We…

Given a black-box classification model and an unlabeled evaluation dataset from some application domain, efficient strategies need to be developed to evaluate the model. Random sampling allows a user to estimate metrics like accuracy,…

Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenarios has led to interesting advancement, it has not been able…

We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiring modifications during inference. Unlike prior approaches…

Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue with these approaches is that they are weak in…

With the success of image generation, generative diffusion models are increasingly adopted for discriminative tasks, as pixel generation provides a unified perception interface. However, directly repurposing the generative denoising process…

We aim to determine some physical properties of distant galaxies (for example, stellar mass, star formation history, or chemical enrichment history) from their observed spectra, using supervised machine learning methods. We know that…

Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques. They pose severe security problems for deep learning applications because they can effectively bypass defense mechanisms.…

We are considering in this paper the task of label-efficient fine-tuning of segmentation models: We assume that a large labeled dataset is available and allows to train an accurate segmentation model in one domain, and that we have to adapt…

Label noise poses an important challenge in machine learning, especially in deep learning, in which large models with high expressive power dominate the field. Models of that kind are prone to memorizing incorrect labels, thereby harming…

The problem of labeled graph generation is gaining attention in the Deep Learning community. The task is challenging due to the sparse and discrete nature of graph spaces. Several approaches have been proposed in the literature, most of…

In this paper, we first collect and track a large number of fixed and unfixed violations across revisions of software. The empirical analyses reveal that there are discrepancies in the distributions of violations that are detected and those…