all AI news
Extreme Miscalibration and the Illusion of Adversarial Robustness
Feb. 28, 2024, 5:49 a.m. | Vyas Raina, Samson Tan, Volkan Cevher, Aditya Rawal, Sheng Zha, George Karypis
cs.CL updates on arXiv.org arxiv.org
Abstract: Deep learning-based Natural Language Processing (NLP) models are vulnerable to adversarial attacks, where small perturbations can cause a model to misclassify. Adversarial Training (AT) is often used to increase model robustness. However, we have discovered an intriguing phenomenon: deliberately or accidentally miscalibrating models masks gradients in a way that interferes with adversarial attack search methods, giving rise to an apparent increase in robustness. We show that this observed gain in robustness is an illusion of …
abstract adversarial adversarial attacks adversarial training arxiv attacks cs.cl deep learning language language processing masks model robustness natural natural language natural language processing nlp processing robustness small training type vulnerable
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne