most citedReleasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning

2 citations · 2 across the 2 of their papers we have counts for

collaborators

1 paper

cs.CL2025

Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework

Binhao Ma, Hanqing Guo, Zhengping Jay Luo +1

Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced the naturalness and flexibility of human computer interaction by enabling seamless understan…