BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
Paper • 2506.02479 • Published
Kalyan Nakka
kalyannakka
AI & ML interests
Adversarial Machine Learning and AI Security
Recent Activity
updated a collection about 2 hours ago
quantization_models updated a collection about 2 hours ago
quantization_models updated a collection about 2 hours ago
quantization_modelsOrganizations
authored a
paper 10 months ago