Today's article comes from the journal of Cybersecurity. The authors are Wang et al., from Nanjing University of Science and Technology, in China. In this paper they're showcasing a framework for generating adversarial text. It balances attack success with stealth and semantic preservation, rather than optimizing for any one of those in isolation.
DOI: 10.1186/s42400-025-00500-3
You must be an active Journal Club member to access this content. If you're already a member, click the blue button to login. If you're not a member yet, click the sign-up button to get started.
Login to My Account
Sign Up