arXiv subjects

Hua Dai

Publications and source records attributed to Hua Dai.

6 recordsLinked to original sources

arXiv2026

Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks

The safety alignment of Large Language Models (LLMs) remains vulnerable to Harmful Fine-tuning (HFT). While existing defenses impose constraints on parameters, gradients, or internal representations, we observe that they can be effectively circumvented under persistent HFT. Our analysis traces this failure to the inherent redundancy of the high-dimensional parameter space: attackers exploit optimization trajectories that are orthogonal to defense constraints to restore harmful capabilities while deceptively adhering to safety restrictions. To address this, we propose Safety Bottleneck Regularization (SBR). SBR shifts the defensive focus from the redundant parameter space to the unembedding layer, which serves as a geometric bottleneck. By anchoring the final hidden states of harmful queries to those of the safety-aligned model, SBR enables the model to maintain safe responses even under persistent HFT. Extensive experiments confirm SBR's effectiveness, demonstrating that utilizing just a single safety anchor is sufficient to reduce the Harmful Score to $<$10 while preserving competitive performance on benign downstream tasks.

cs.CR↗

arXiv2026

PAC-DP: Personalized Adaptive Clipping for Differentially Private Federated Learning

Differential privacy (DP) is crucial for safeguarding sensitive client information in federated learning (FL), yet traditional DP-FL methods rely predominantly on fixed gradient clipping thresholds. Such static clipping neglects significant client heterogeneity and varying privacy sensitivities, which may lead to an unfavorable privacy-utility trade-off. In this paper, we propose PAC-DP, a Personalized Adaptive Clipping framework for federated learning under record-level local differential privacy. PAC-DP introduces a Simulation-CurveFitting approach leveraging a server-hosted public proxy dataset to learn an effective mapping between personalized privacy budgets epsilon and gradient clipping thresholds C, which is then deployed online with a lightweight round-wise schedule. This design enables budget-conditioned threshold selection while avoiding data-dependent tuning during training. We provide theoretical analyses establishing convergence guarantees under the per-example clipping and Gaussian perturbation mechanism and a reproducible privacy accounting procedure. Extensive evaluations on multiple FL benchmarks show that PAC-DP surpasses conventional fixed-threshold approaches under matched privacy budgets, improving accuracy by up to 26% and accelerating convergence by up to 45.5% in our evaluated settings.

cs.CR↗

arXiv2025

An Efficient Proximity Graph-based Approach to Table Union Search

Neural embedding models are extensively employed in the table union search problem, which aims to find semantically compatible tables that can be merged with a given query table. In particular, multi-vector models, which represent a table as a vector set (typically one vector per column), have been demonstrated to achieve superior retrieval quality by capturing fine-grained semantic alignments. However, this problem faces more severe efficiency challenges than the single-vector problem due to the inherent dependency on bipartite graph maximum matching to compute unionability scores. Therefore, this paper proposes an efficient Proximity Graph-based Table Union Search (PGTUS) approach. PGTUS employs a multi-stage pipeline that combines a novel refinement strategy, a filtering strategy based on many-to-one bipartite matching. Besides, we propose an enhanced pruning strategy to prune the candidate set, which further improve the search efficiency. Extensive experiments on six benchmark datasets demonstrate that our approach achieves 3.6-6.0X speedup over existing approaches while maintaining comparable recall rates.

cs.DB↗

arXiv2025

A Survey on Open Dataset Search in the LLM Era: Retrospectives and Perspectives

High-quality datasets are typically required for accomplishing data-driven tasks, such as training medical diagnosis models, predicting real-time traffic conditions, or conducting experiments to validate research hypotheses. Consequently, open dataset search, which aims to ensure the efficient and accurate fulfillment of users' dataset requirements, has emerged as a critical research challenge and has attracted widespread interest. Recent studies have made notable progress in enhancing the flexibility and intelligence of open dataset search, and large language models (LLMs) have demonstrated strong potential in addressing long-standing challenges in this area. Therefore, a systematic and comprehensive review of the open dataset search problem is essential, detailing the current state of research and exploring future directions. In this survey, we focus on recent advances in open dataset search beyond traditional approaches that rely on metadata and keywords. From the perspective of dataset modalities, we place particular emphasis on example-based dataset search, advanced similarity measurement techniques based on dataset content, and efficient search acceleration techniques. In addition, we emphasize the mutually beneficial relationship between LLMs and open dataset search. On the one hand, LLMs help address complex challenges in query understanding, semantic modeling, and interactive guidance within open dataset search. In turn, advances in dataset search can support LLMs by enabling more effective integration into retrieval-augmented generation (RAG) frameworks and data selection processes, thereby enhancing downstream task performance. Finally, we summarize open research problems and outline promising directions for future work. This work aims to offer a structured reference for researchers and practitioners in the field of open dataset search.

cs.IR↗

arXiv2024

A Wind-Aware Path Planning Method for UAV-Asisted Bridge Inspection

In response to the gap in considering wind conditions in the bridge inspection using unmanned aerial vehicle (UAV) , this paper proposes a path planning method for UAVs that takes into account the influence of wind, based on the simulated annealing algorithm. The algorithm considers the wind factors, including the influence of different wind speeds and directions at the same time on the path planning of the UAV. Firstly, An environment model is constructed specifically for UAV bridge inspection, taking into account the various objective functions and constraint conditions of UAVs. A more sophisticated and precise mathematical model is then developed based on this environmental model to enable efficient and effective UAV path planning. Secondly, the bridge separation planning model is applied in a novel way, and a series of parameters are simulated, including the adjustment of the initial temperature value. The experimental results demonstrate that, compared with traditional local search algorithms, the proposed method achieves a cost reduction of 30.05\% and significantly improves effectiveness. Compared to path planning methods that do not consider wind factors, the proposed approach yields more realistic and practical results for UAV applications, as demonstrated by its improved effectiveness in simulations. These findings highlight the value of our method in facilitating more accurate and efficient UAV path planning in wind-prone environments.

eess.SY↗

arXiv2021

Generating Unrestricted 3D Adversarial Point Clouds

Utilizing 3D point cloud data has become an urgent need for the deployment of artificial intelligence in many areas like facial recognition and self-driving. However, deep learning for 3D point clouds is still vulnerable to adversarial attacks, e.g., iterative attacks, point transformation attacks, and generative attacks. These attacks need to restrict perturbations of adversarial examples within a strict bound, leading to the unrealistic adversarial 3D point clouds. In this paper, we propose an Adversarial Graph-Convolutional Generative Adversarial Network (AdvGCGAN) to generate visually realistic adversarial 3D point clouds from scratch. Specifically, we use a graph convolutional generator and a discriminator with an auxiliary classifier to generate realistic point clouds, which learn the latent distribution from the real 3D data. The unrestricted adversarial attack loss is incorporated in the special adversarial training of GAN, which enables the generator to generate the adversarial examples to spoof the target network. Compared with the existing state-of-art attack methods, the experiment results demonstrate the effectiveness of our unrestricted adversarial attack methods with a higher attack success rate and visual quality. Additionally, the proposed AdvGCGAN can achieve better performance against defense models and better transferability than existing attack methods with strong camouflage.

cs.CV↗