arXiv - CSCL: "Exploiting Explainability to Design Adversarial A…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Exploiting Explainability to Design Adversarial Attacks and Evaluate Attack Resilience in Hate-Speech Detection Models. (arXiv:2305.18585v1 [cs.CL])

http://arxiv.org/abs/2305.18585 #arXiv #NLProc

May 31, 2023, 03:10 · · arxiv-cscl · · ·

Sign in to participate in the conversation