Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks

arXiv:2402.09874v1 Announce Type: new
Abstract: Adversarial attacks represent a substantial challenge in Natural Language Processing (NLP). This study undertakes a systematic exploration of this challenge in two distinct phases: vulnerability evaluation and resilience enhancement of Transformer-based models under adversarial attacks.
In the evaluation phase, we assess the susceptibility of three Transformer configurations, encoder-decoder, encoder-only, and decoder-only setups, to adversarial attacks of escalating complexity across datasets containing offensive language and misinformation. Encoder-only models manifest a 14% and 21% performance drop in …

abstract adversarial adversarial attacks arxiv attacks challenge cs.cl evaluation exploration language language model language processing model robustness natural natural language natural language processing nlp processing resilience robustness study transformer type vulnerability