Daizong Liu
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1ML×1Stats ML×1
Frequent co-authors
Research Timeline
2026
Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
The paper proposes FRA-Attack, a frequency-domain regularization method, to significantly improve the transferability of adversarial attacks against closed-source Multimodal Large Language Models (MLLMs).
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIcs.LGRecentMay 20, 2026
Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
Leitao Yuan, Qinghua Mao, Daizong Liu, Kun Wang +4 more
The paper proposes FRA-Attack, a frequency-domain regularization method, to significantly improve the transferability of adversarial attacks against closed-source Multimodal Large Language Models (MLL…
View →