Generative Textual Adversarial Attack Through Extensible Compositional Perturbation via Reinforcement Learning for Policy Optimization

Researchers developed GECOMP, a method that uses reinforcement learning (a technique where an AI learns by receiving rewards for good actions) to generate adversarial examples (inputs designed to trick AI models) against natural language processing systems. The method creates perturbations (small changes to text) using a library of possible edits and an LLM (large language model) generator, balancing the goal of fooling the target model while maintaining text quality and minimizing the number of queries needed to test it.