ServiceNow Research

Adversarial Attacks

Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning
The rise of foundation models fine-tuned on human feedback from potentially untrusted users has increased the risk of adversarial data …
Constraining Representations Yields Models That Know What They Don't Know
A well-known failure mode of neural networks is that they may confidently return erroneous predictions. Such unsafe behaviour is …
Maximal Jacobian-based Saliency Map Attack
The Jacobian-based Saliency Map Attack is a family of adversarial attack methods for fooling classification models, such as deep neural …