EntropyScan detects backdoored LVLMs by quantifying structural anomalies in visual attention distributions on benign samples via Tsallis entropy and reference-anchored Z-score normalization.
In: ICML (2023)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4representative citing papers
Topo-R1 fine-tunes a vision-language model using a topology-aware reward and GRPO to detect anomalies such as broken or spurious connections in tubular segmentation masks, outperforming standard VLMs.
SCENT uses VLM-generated scene descriptions as a semantic bridge to align electronic-nose signals with visual and textual embeddings, improving cross-modal smell retrieval and enabling object-context odor disentanglement.
HyFL-CLIP distills Euclidean CLIP alignment into hyperbolic space using cross-manifold similarity and Einstein midpoint aggregation to capture hierarchical part-whole relations, achieving up to 19.5% gains in long-text retrieval under perturbations.
citing papers explorer
-
EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy
EntropyScan detects backdoored LVLMs by quantifying structural anomalies in visual attention distributions on benign samples via Tsallis entropy and reference-anchored Z-score normalization.
-
Topo-R1: Detecting Topological Anomalies via Vision-Language Models
Topo-R1 fine-tunes a vision-language model using a topology-aware reward and GRPO to detect anomalies such as broken or spurious connections in tubular segmentation masks, outperforming standard VLMs.
-
What Images Cannot Say: Language-Guided Olfactory Representation Learning
SCENT uses VLM-generated scene descriptions as a semantic bridge to align electronic-nose signals with visual and textual embeddings, improving cross-modal smell retrieval and enabling object-context odor disentanglement.
-
HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding
HyFL-CLIP distills Euclidean CLIP alignment into hyperbolic space using cross-manifold similarity and Einstein midpoint aggregation to capture hierarchical part-whole relations, achieving up to 19.5% gains in long-text retrieval under perturbations.