Preserving Cross-Modal Stability for Visual Unlearning in Multimodal Scenarios
This addresses privacy leakage in multimodal systems like autonomous driving, but it is incremental as it builds on existing unlearning methods.
The paper tackles the problem of visual unlearning in multimodal applications, where existing methods reduce performance by failing to preserve cross-modal knowledge and intra-class stability, and proposes a Cross-modal Contrastive Unlearning framework that achieves a 7.12% accuracy improvement with only 7% of the unlearning time compared to the top-accuracy baseline.
Visual modality is the most vulnerable to privacy leakage in real-world multimodal applications like autonomous driving with visual and radar data; Machine unlearning removes specific training data from pre-trained models to address privacy leakage, however, existing methods fail to preserve cross-modal knowledge and maintain intra-class structural stability of retain data, leading to reduced overall and other modalities' performance during visual unlearning; to address these challenges, we propose a Cross-modal Contrastive Unlearning (CCU) framework, which integrates three key components: (a) selective visual unlearning: employing inverse contrastive learning to dissociate visual representations from their original semantics, (b) cross-modal knowledge retention: preserving other modalities' discriminability through semantic consistency, and (c) dual-set contrastive separation: preserving the model performance via isolation of structural perturbations between the unlearn set and retain set; extensive experiments on three datasets demonstrate the superiority of CCU, and our method achieves a 7.12% accuracy improvement with only 7% of the unlearning time compared to the top-accuracy baseline.