Related papers: Outlier Robust Adversarial Training
Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time. Existing methods learn model parameters iteratively through stochastic gradient…
Deep learning models exhibit a preference for statistical fitting over logical reasoning. Spurious correlations might be memorized when there exists statistical bias in training data, which severely limits the model performance especially…
Adversarial training yields robust models against a specific threat model, e.g., $L_\infty$ adversarial examples. Typically robustness does not generalize to previously unseen threat models, e.g., other $L_p$ norms, or larger perturbations.…
The existence of adversarial examples points to a basic weakness of deep neural networks. One of the most effective defenses against such examples, adversarial training, entails training models with some degree of robustness, usually at the…
Model robustness against adversarial examples of single perturbation type such as the $\ell_{p}$-norm has been widely studied, yet its generalization to more realistic scenarios involving multiple semantic perturbations and their…
Adversarial training (AT) is always formulated as a minimax problem, of which the performance depends on the inner optimization that involves the generation of adversarial examples (AEs). Most previous methods adopt Projected Gradient…
The optimization of large language models (LLMs) remains a critical challenge, particularly as model scaling exacerbates sensitivity to algorithmic imprecision and training instability. Recent advances in optimizers have improved…
Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify…
Model-based reinforcement learning has attracted much attention due to its high sample efficiency and is expected to be applied to real-world robotic applications. In the real world, as unobservable disturbances can lead to unexpected…
Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in an open-world setting. However, existing OOD detection solutions can be brittle in the open world, facing various types of adversarial OOD…
In the last a few decades, deep neural networks have achieved remarkable success in machine learning, computer vision, and pattern recognition. Recent studies however show that neural networks (both shallow and deep) may be easily fooled by…
Domain adversarial training has shown its effective capability for finding domain invariant feature representations and been successfully adopted for various domain adaptation tasks. However, recent advances of large models (e.g., vision…
Adversarial Training (AT) has been found to substantially improve the robustness of deep learning classifiers against adversarial attacks. AT involves obtaining robustness by including adversarial examples in training a classifier. Most…
Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…
Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space without committing to a specific adversarial class, wasting queries on diffuse, undirected…
Adversarial training is a popular method to give neural nets robustness against adversarial perturbations. In practice adversarial training leads to low robust training loss. However, a rigorous explanation for why this happens under…
Recent work have demonstrated that robustness (to "corruption") can be at odds with generalization. Adversarial training, for instance, aims to reduce the problematic susceptibility of modern neural networks to small data perturbations.…
We introduce random adversarial training (RAT), a novel framework successfully applied to biomedical information extraction (BioIE) tasks. Building on PubMedBERT as the foundational architecture, our study first validates the effectiveness…
Many variants of adversarial training have been proposed, with most research focusing on problems with relatively few classes. In this paper, we propose Two Head Adversarial Training (THAT), a two-stream adversarial learning network that is…
Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the…