Xinguo Feng, Zhongkui Ma, Zihan Wang, Alsharif Abuadbba, Guangdong Bai. Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation. In Manindra Agrawal, Ian Molloy, Vinayaka Pandit, Debdeep Mukhopadhyay, Kenny Paterson, editors, Proceedings of the ACM Asia Conference on Computer and Communications Security, ASIA CCS 2026, Bangalore, India, June 1-5, 2026. pages 1832-1848, ACM, 2026. [doi]
Abstract is missing.