Kavli Affiliate: Zhuo Li | First 5 Authors: Huizhen Shu, Huizhen Shu, , , | Summary: With the rapid proliferation of Natural Language Processing (NLP), especially Large Language Models (LLMs), generating adversarial examples to jailbreak LLMs remains a key challenge for understanding model vulnerabilities and improving robustness. In this context, we propose a new black-box […]
Continue.. Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation