相关论文: PEARL: Preprocessing Enhanced Adversarial Robust L…

We present an adversarial framework to craft perturbations that mislead classifiers by accounting for the image content and the semantics of the labels. The proposed framework combines a structure loss and a semantic adversarial loss in a…

Generalization and robustness are both key desiderata for designing machine learning methods. Adversarial training can enhance robustness, but past work often finds it hurts generalization. In natural language processing (NLP), pre-training…

With the rise in popularity of machine and deep learning models, there is an increased focus on their vulnerability to malicious inputs. These adversarial examples drift model predictions away from the original intent of the network and are…

Due to the limited and even imbalanced data, semi-supervised semantic segmentation tends to have poor performance on some certain categories, e.g., tailed categories in Cityscapes dataset which exhibits a long-tailed label distribution.…

Despite their effectiveness in a wide range of tasks, deep architectures suffer from some important limitations. In particular, they are vulnerable to catastrophic forgetting, i.e. they perform poorly when they are required to update their…

Large Language Models show great potential with external tools, but face significant challenges in complex, multi-turn tool invocation. They often exhibit weak planning, tool hallucination, erroneous parameter generation, and struggle with…

Although deep neural networks have achieved super-human performance on many classification tasks, they often exhibit a worrying lack of robustness towards adversarially generated examples. Thus, considerable effort has been invested into…

In practice, deep neural networks have been found to be vulnerable to various types of noise, such as adversarial examples and corruption. Various adversarial defense methods have accordingly been developed to improve adversarial robustness…

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…

Thermal imaging is often compromised by dynamic, complex degradations caused by hardware limitations and unpredictable environmental factors. The scarcity of high-quality infrared data, coupled with the challenges of dynamic, intricate…

Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

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…

Catastrophic forgetting of previous knowledge is a critical issue in continual learning typically handled through various regularization strategies. However, existing methods struggle especially when several incremental steps are performed.…

Semantic segmentation methods have achieved outstanding performance thanks to deep learning. Nevertheless, when such algorithms are deployed to new contexts not seen during training, it is necessary to collect and label scene-specific data…

Deep neural networks, like many other machine learning models, have recently been shown to lack robustness against adversarially crafted inputs. These inputs are derived from regular inputs by minor yet carefully selected perturbations that…

Contrastive learning is an effective unsupervised method in graph representation learning, and the key component of contrastive learning lies in the construction of positive and negative samples. Previous methods usually utilize the…

The effects of adversarial training on semantic segmentation networks has not been thoroughly explored. While previous work has shown that adversarially-trained image classifiers can be used to perform image synthesis, we have yet to…

Most state-of-the-art semantic segmentation approaches only achieve high accuracy in good conditions. In practically-common but less-discussed adverse environmental conditions, their performance can decrease enormously. Existing studies…

We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features,…