Introduces Targeted Downstream-Agnostic Attack (TDAA) that uses a threat image as feature anchor and example-specific perturbations to achieve targeted attacks on unknown downstream tasks from pre-trained encoders.
Deep residual learning for image recognition,
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
verdicts
UNVERDICTED 8representative citing papers
STFER uses LVLM-generated identity-consistent semantic text to drive visual token filtering and expert routing for improved any-time person re-identification under clothing changes and modality shifts.
Multi-stage residual learning in quantum circuits mitigates frequency parameterization bias and improves test MSE on synthetic benchmarks with multiple localized frequency components compared to single-stage training.
TinyUSFM distills a large ultrasound foundation model into a lightweight version using feature-gradient coreset selection and domain-separated masked image modeling, matching performance on a new 18-dataset benchmark with 6.36% of the parameters.
A complete pipeline for federated unlearning via knowledge distillation for efficient removal and a GAN-integrated classifier for visual evaluation of forgetting capacity.
Intelligence Inertia models the computational resistance to structural change in neural networks via a heuristic relativistic analogy, yielding a J-shaped cost curve that diverges from classical approximations.
AV-Master introduces dynamic adaptive focus sampling, modality preference modeling, and dual-path contrastive loss to outperform prior methods on audio-visual question answering benchmarks.
Perceptual quality metrics correlate strongly with each other but show minimal correlation with attack success rate across medical imaging models and datasets, making ASR alone inadequate for assessing adversarial robustness.
citing papers explorer
-
Targeted Downstream-Agnostic Attack
Introduces Targeted Downstream-Agnostic Attack (TDAA) that uses a threat image as feature anchor and example-specific perturbations to achieve targeted attacks on unknown downstream tasks from pre-trained encoders.
-
Beyond Visual Cues: Semantic-Driven Token Filtering and Expert Routing for Anytime Person ReID
STFER uses LVLM-generated identity-consistent semantic text to drive visual token filtering and expert routing for improved any-time person re-identification under clothing changes and modality shifts.
-
Mitigating Frequency Learning Bias in Quantum Models via Multi-Stage Residual Learning
Multi-stage residual learning in quantum circuits mitigates frequency parameterization bias and improves test MSE on synthetic benchmarks with multiple localized frequency components compared to single-stage training.
-
TinyUSFM: Towards Compact and Efficient Ultrasound Foundation Models
TinyUSFM distills a large ultrasound foundation model into a lightweight version using feature-gradient coreset selection and domain-separated masked image modeling, matching performance on a new 18-dataset benchmark with 6.36% of the parameters.
-
Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation
A complete pipeline for federated unlearning via knowledge distillation for efficient removal and a GAN-integrated classifier for visual evaluation of forgetting capacity.
-
Intelligence Inertia: Physical Isomorphism and Applications
Intelligence Inertia models the computational resistance to structural change in neural networks via a heuristic relativistic analogy, yielding a J-shaped cost curve that diverges from classical approximations.
-
AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering
AV-Master introduces dynamic adaptive focus sampling, modality preference modeling, and dual-path contrastive loss to outperform prior methods on audio-visual question answering benchmarks.
-
Beyond Attack Success Rate: A Multi-Metric Evaluation of Adversarial Transferability in Medical Imaging Models
Perceptual quality metrics correlate strongly with each other but show minimal correlation with attack success rate across medical imaging models and datasets, making ASR alone inadequate for assessing adversarial robustness.