Good models require good training data. For overparameterized deep models, the causal
relationship between training data and model predictions is increasingly opaque and poorly …

Retrieval-augmented generation (RAG) has been shown vulnerable to retrieval corruption
attacks: an attacker can inject malicious passages into retrieval results to induce inaccurate …

Sparse or L0 adversarial attacks arbitrarily perturb an unknown subset of the features. L0
robustness analysis is particularly well-suited for heterogeneous (tabular) data where …

Images have become a significant medium for information transmission, while image
forensics has garnered widespread attention from researchers. Due to the scarcity of finely …

Generalization of machine learning models can be severely compromised by data
poisoning, where adversarial changes are applied to the training data. This vulnerability has …

Few-shot classification with foundation models (eg, CLIP, DINOv2, PaLM-2) enables users
to build an accurate classifier with a few labeled training samples (called support samples) …

Sparse or $\ell_0 $ adversarial attacks arbitrarily perturb an unknown subset of the features.
$\ell_0 $ robustness analysis is particularly well-suited for heterogeneous (tabular) data …

Visual prompting (VP) is a new technique that adapts well-trained frozen models for source
domain tasks to target domain tasks. This study examines VP's benefits for black-box model …

Sparse or $\ell_0 $ adversarial attacks arbitrarily perturb an unknown subset of the features.
$\ell_0 $ robustness analysis is particularly well-suited for heterogeneous (tabular) data …

In recent years, machine learning systems have been developed that demonstrate
remarkable performance on many tasks. However, naive metrics of performance, such as …