Selected work

Representative Papers

Estimation is Not Enough: Carpet-Bombing Detection via Per-Packet Uniformity Testing

Sep 27, 2026

This study addresses the high detection latency of carpet bombing attacks and the failure of conventional methods caused by source address spoofing. To overcome these limitations, this work proposes SweepSketch, the first sketch-based real-time detection model. By anchoring at the destination end without maintaining per-source state, the architecture achieves structural immunity to source address spoofing. SweepSketch integrates T-HLL, CUSUM decision logic, and dual-EWMA gating techniques, and is deployed on a Tofino2 programmable switch to enable line-rate processing. Experimental evaluations demonstrate that SweepSketch attains an F1 score of 0.991 with a median alert delay of merely 186–627 ms, successfully identifying all victim prefixes. Overall, its comprehensive performance significantly surpasses that of existing baselines.

0 citationsRead paper

Few-Shot Video Recognition via Hierarchical Metric Learning

Sep 04, 2026

本文针对少样本视频识别问题，提出了一种层次度量学习方法HML-FSAR，通过增强空间模块和多层次度量策略来优化特征紧凑性和类别区分性。

0 citationsRead paper

DiEC: Diffusion Embedded Clustering

Dec 23, 2025

Existing deep clustering methods rely on a single encoder to produce static embeddings, overlooking the discriminative clustering potential embedded in the dynamic representation trajectories of pretrained diffusion models—specifically, their layer-wise and noise-step-wise internal activations. This paper proposes DiEC, the first method to directly leverage the two-dimensional (layer–time) internal activations of diffusion models for unsupervised clustering. DiEC employs weakly coupled decomposition and a two-stage search (CML + OTS) to identify clustering-favorable bottleneck layers and optimal denoising timesteps. To enhance representation separability and structural robustness, it introduces denoising consistency regularization, adaptive graph regularization, and entropy regularization. Evaluated on multiple benchmarks, DiEC achieves state-of-the-art or leading performance, significantly outperforming conventional clustering paradigms based on fixed embeddings.

0 citationsRead paper

DCSCR: A Class-Specific Collaborative Representation based Network for Image Set Classification

Aug 18, 2025

Image set classification (ISC) faces two key challenges: insufficient feature representation learning and non-adaptive inter-set similarity measurement—particularly limiting performance in few-shot settings. To address these, we propose a novel few-shot ISC framework that synergistically integrates deep learning with classical collaborative representation. Our approach is the first to embed class-specific collaborative representation (CSCR) into an end-to-end deep network, enabling adaptive concept-level feature refinement and joint optimization of inter-set distances. The framework comprises three core components: a fully convolutional feature extractor, a global feature aggregator, and a CSCR-based metric learning module, augmented by a newly designed CSCR contrastive loss. Extensive experiments on multiple mainstream few-shot ISC benchmarks demonstrate significant improvements over state-of-the-art methods, validating both effectiveness and robustness.

0 citationsRead paper

Conformal Sets in Multiple-Choice Question Answering under Black-Box Settings with Provable Coverage Guarantees

Aug 07, 2025

Large language models (LLMs) frequently exhibit hallucination and overconfidence in multiple-choice question answering (MCQA), undermining their reliability. Method: We propose a black-box, model-agnostic uncertainty quantification method grounded in answer-frequency statistics—replacing logit-based probabilities with empirical frequencies from multiple independent samplings to construct a distribution-free conformal prediction framework. The prediction set is derived from the entropy of the most frequent answer, ensuring theoretically guaranteed coverage. Results: Evaluated across six mainstream LLMs and four MCQA benchmarks, our approach significantly outperforms logit-based baselines, achieving substantial AUROC improvements while empirically satisfying the prescribed risk level for miscoverage. This provides a verifiable, theoretically sound solution for trustworthy reasoning in high-stakes applications.

0 citationsRead paper

Recent publications

Latest Papers

Estimation is Not Enough: Carpet-Bombing Detection via Per-Packet Uniformity Testing

Sep 27, 2026

This study addresses the high detection latency of carpet bombing attacks and the failure of conventional methods caused by source address spoofing. To overcome these limitations, this work proposes SweepSketch, the first sketch-based real-time detection model. By anchoring at the destination end without maintaining per-source state, the architecture achieves structural immunity to source address spoofing. SweepSketch integrates T-HLL, CUSUM decision logic, and dual-EWMA gating techniques, and is deployed on a Tofino2 programmable switch to enable line-rate processing. Experimental evaluations demonstrate that SweepSketch attains an F1 score of 0.991 with a median alert delay of merely 186–627 ms, successfully identifying all victim prefixes. Overall, its comprehensive performance significantly surpasses that of existing baselines.

0 citationsRead paper

Few-Shot Video Recognition via Hierarchical Metric Learning

Sep 04, 2026

本文针对少样本视频识别问题，提出了一种层次度量学习方法HML-FSAR，通过增强空间模块和多层次度量策略来优化特征紧凑性和类别区分性。

0 citationsRead paper

DiEC: Diffusion Embedded Clustering

Dec 23, 2025

Existing deep clustering methods rely on a single encoder to produce static embeddings, overlooking the discriminative clustering potential embedded in the dynamic representation trajectories of pretrained diffusion models—specifically, their layer-wise and noise-step-wise internal activations. This paper proposes DiEC, the first method to directly leverage the two-dimensional (layer–time) internal activations of diffusion models for unsupervised clustering. DiEC employs weakly coupled decomposition and a two-stage search (CML + OTS) to identify clustering-favorable bottleneck layers and optimal denoising timesteps. To enhance representation separability and structural robustness, it introduces denoising consistency regularization, adaptive graph regularization, and entropy regularization. Evaluated on multiple benchmarks, DiEC achieves state-of-the-art or leading performance, significantly outperforming conventional clustering paradigms based on fixed embeddings.

0 citationsRead paper

DCSCR: A Class-Specific Collaborative Representation based Network for Image Set Classification

Aug 18, 2025

Image set classification (ISC) faces two key challenges: insufficient feature representation learning and non-adaptive inter-set similarity measurement—particularly limiting performance in few-shot settings. To address these, we propose a novel few-shot ISC framework that synergistically integrates deep learning with classical collaborative representation. Our approach is the first to embed class-specific collaborative representation (CSCR) into an end-to-end deep network, enabling adaptive concept-level feature refinement and joint optimization of inter-set distances. The framework comprises three core components: a fully convolutional feature extractor, a global feature aggregator, and a CSCR-based metric learning module, augmented by a newly designed CSCR contrastive loss. Extensive experiments on multiple mainstream few-shot ISC benchmarks demonstrate significant improvements over state-of-the-art methods, validating both effectiveness and robustness.

0 citationsRead paper

Conformal Sets in Multiple-Choice Question Answering under Black-Box Settings with Provable Coverage Guarantees

Aug 07, 2025

Large language models (LLMs) frequently exhibit hallucination and overconfidence in multiple-choice question answering (MCQA), undermining their reliability. Method: We propose a black-box, model-agnostic uncertainty quantification method grounded in answer-frequency statistics—replacing logit-based probabilities with empirical frequencies from multiple independent samplings to construct a distribution-free conformal prediction framework. The prediction set is derived from the entropy of the most frequent answer, ensuring theoretically guaranteed coverage. Results: Evaluated across six mainstream LLMs and four MCQA benchmarks, our approach significantly outperforms logit-based baselines, achieving substantial AUROC improvements while empirically satisfying the prescribed risk level for miscoverage. This provides a verifiable, theoretically sound solution for trustworthy reasoning in high-stakes applications.

0 citationsRead paper