Multimodal Large Language Models (MLLMs) are increasingly deployed in safety-critical domains, yet their susceptibility to backdoor attacks remains a formidable challenge. While existing defenses h...
<p><strong>Tác giả:</strong> Yinzhen Huang, Jiahe Xie, Yitong Sun, Ruochen Zhang, Xingxing Wei</p>
<p>Multimodal Large Language Models (MLLMs) are increasingly deployed in safety-critical domains, yet their susceptibility to backdoor attacks remains a formidable challenge. While existing defenses have evolved from visual-centric patch cues to unsupervised internal attention statistics, they are fundamentally constrained by a reliance on static snapshots and attack-specific heuristics. Given the intricate interplay between dual modalities, the vast design space for multimodal triggers allows d...</p>
<p>📄 DOI: <a href="https://doi.org/https://doi.org/10.1145/3767308.3836209" target="_blank" rel="noopener">https://doi.org/10.1145/3767308.3836209</a></p>
<p>📖 <a href="https://doi.org/https://doi.org/10.1145/3767308.3836209" target="_blank" rel="noopener">Xem bài báo đầy đủ</a></p>
Bài viết được biên soạn lại bởi LIFVietnam. Nguồn tham khảo: OpenAlex
