Robust Nearest Neighbour Retrieval Using Targeted Manifold Manipulation
This addresses retrieval robustness for AI pipelines, though it appears incremental as it builds on existing perturbation and backdooring concepts.
The paper tackles the problem of nearest-neighbour retrieval in classification and explainable-AI by proposing TMM-NN, which uses targeted perturbations to define neighbourhoods based on sample responsiveness rather than geometric distance, resulting in improved performance under noise and across diverse tasks as confirmed by benchmark experiments.
Nearest-neighbour retrieval is central to classification and explainable-AI pipelines, but current practice relies on hand-tuning feature layers and distance metrics. We propose Targeted Manifold Manipulation-Nearest Neighbour (TMM-NN), which reconceptualises retrieval by assessing how readily each sample can be nudged into a designated region of the feature manifold; neighbourhoods are defined by a sample's responsiveness to a targeted perturbation rather than absolute geometric distance. TMM-NN implements this through a lightweight, query-specific trigger patch. The patch is added to the query image, and the network is weakly ``backdoored'' so that any input with the patch is steered toward a dummy class. Images similar to the query need only a slight shift and are classified as the dummy class with high probability, while dissimilar ones are less affected. By ranking candidates by this confidence, TMM-NN retrieves the most semantically related neighbours. Robustness analysis and benchmark experiments confirm this trigger-based ranking outperforms traditional metrics under noise and across diverse tasks.