Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
Researchers have developed FRA-Attack, a novel method to improve the transferability of adversarial attacks against multimodal large language models (MLLMs). This technique utilizes frequency-domain regularization to align perturbations with shared visual cues across different models, overcoming limitations of existing spatial-domain approaches. Experiments on 15 MLLMs demonstrate FRA-Attack's superior performance, particularly against models like GPT-5.4, Claude-Opus-4.6, and Gemini-3-flash. AI
IMPACT Enhances understanding of MLLM vulnerabilities and informs security research.