arXiv Open Access 2023

Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks

Piotr Gaiński Klaudia Bałazy

Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

cs.CL

Penulis (2)

Piotr Gaiński

Klaudia Bałazy

Format Sitasi

APA MLA BibTeX

Gaiński, P., Bałazy, K. (2023). Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks. https://arxiv.org/abs/2302.05120

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2023
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓