Year: 2023
Type: conference-paper
Abstract: We propose a novel gradient-based attack against transformer-based language models that searches for an adversarial example in a continuous space of token probabilities.Our algorithm mitigates the gap between adversarial loss for continuous and discrete text representations by performing multi-step quantization in a quantization-compensation loop.Experiments show that our method significantly outperforms other approaches on various natural language processing (NLP) tasks.
Authors: Piotr Gaiński, Klaudia Bałazy
Institution: Jagiellonian University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: G2015427213, G735078438
OpenAlex ID: W4386566751
