There have been two competing paradigms in artificial intelligence (AI) development ever
since its birth in 1956, ie, symbolism and connectionism (or sub-symbolism). While …

Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption,
with machine learning systems demonstrating superhuman performance in a significant …

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented
performance in response generation, especially with visual inputs, enabling more creative …

Recent work argues that robust training requires substantially larger datasets than those
required for standard classification. On CIFAR-10 and CIFAR-100, this translates into a …

This paper explores a better prediction target for BERT pre-training of vision transformers.
We observe that current prediction targets disagree with human perception judgment. This …

Adversarial training suffers from robust overfitting, a phenomenon where the robust test
accuracy starts to decrease during training. In this paper, we focus on reducing robust …

Deep neural networks are vulnerable to adversarial examples that mislead the models with
imperceptible perturbations. Though adversarial attacks have achieved incredible success …

For black-box attacks, the gap between the substitute model and the victim model is usually
large, which manifests as a weak attack performance. Motivated by the observation that the …

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 …

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. It is thus
imperative to devise effective attack algorithms to identify the deficiencies of DNNs …