White-Box Multi-Objective Adversarial Attack on Dialogue Generation. (arXiv:2305.03655v1 [cs.CL])

Pre-trained transformers are popular in state-of-the-art dialogue generation
(DG) systems. Such language models are, however, vulnerable to various
adversarial samples as studied in traditional tasks such as text
classification, which inspires our curiosity about their robustness in DG
systems. One main challenge of attacking DG models is that perturbations on the
current sentence can hardly degrade the response accuracy because the unchanged
chat histories are also considered for decision-making. Instead of merely
pursuing pitfalls of performance metrics such as BLEU, …

adversarial art attack box challenge classification curiosity inspires language language models main popular robustness state systems text transformers vulnerable