Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarization

Yuefang Lian, Longkun Guo, Zhongrui Zhao, Zhigang Lu, Yanan Cai, Shuchao Pang, Dachuan Xu, Jason Xue

Thursday at 04:00

4 Views

0 Comments

arXiv:2606.11804v1 Announce Type: new Abstract: Trustworthy AI requires reliable data-processing pipelines, not only robust downstream predictive models. As an upstream component, data summarization determines which information is retained and passed to subsequent learning or decision modules. Therefore, adversarial perturbations to the...

Read the full article at the source.

Read Original Article

Was this helpful?