Federated learning enables collaborative machine learning while preserving data privacy. However, the rise of federated unlearning, designed to allow clients to erase their data from the global model, introduces new privacy concerns. Specifically, the gradient exchanges during the unlearning process can leak sensitive information about deleted data. In this paper, we introduce DRAGD, a novel attack that exploits gradient discrepancies before and after unlearning to reconstruct forgotten data. We also present DRAGDP, an enhanced version of DRAGD that leverages publicly available prior data to improve reconstruction accuracy, particularly for complex datasets like facial images. Extensive experiments across multiple datasets demonstrate that DRAGD and DRAGDP significantly outperform existing methods in data reconstruction.Our work highlights a critical privacy vulnerability in federated unlearning and offers a practical solution, advancing the security of federated unlearning systems in real-world applications.
Federated learning (FL) enables decentralized machine learning without sharing raw data, allowing multiple clients to collaboratively learn a global model. However, studies reveal that privacy leakage is possible under commonly adopted FL protocols. In particular, a server with access to client gradients can synthesize data resembling the clients' training data. In this paper, we introduce a novel threat model in FL, named the maliciously curious client, where a client manipulates its own gradients with the goal of inferring private data from peers. This attacker uniquely exploits the strength of a Byzantine adversary, traditionally aimed at undermining model robustness, and repurposes it to facilitate data reconstruction attack. We begin by formally defining this novel client-side threat model and providing a theoretical analysis that demonstrates its ability to achieve significant reconstruction success during FL training. To demonstrate its practical impact, we further develop a reconstruction algorithm that combines gradient inversion with malicious update strategies. Our analysis and experimental results reveal a critical blind spot in FL defenses: both server-side robust aggregation and client-side privacy mechanisms may fail against our proposed attack. Surprisingly, standard server- and client-side defenses designed to enhance robustness or privacy may unintentionally amplify data leakage. Compared to the baseline approach, a mistakenly used defense may instead improve the reconstructed image quality by 10-15%.
Federated Learning has emerged as a privacy-oriented alternative to centralized Machine Learning, enabling collaborative model training without direct data sharing. While extensively studied for neural networks, the security and privacy implications of tree-based models remain underexplored. This work introduces TimberStrike, an optimization-based dataset reconstruction attack targeting horizontally federated tree-based models. Our attack, carried out by a single client, exploits the discrete nature of decision trees by using split values and decision paths to infer sensitive training data from other clients. We evaluate TimberStrike on State-of-the-Art federated gradient boosting implementations across multiple frameworks, including Flower, NVFlare, and FedTree, demonstrating their vulnerability to privacy breaches. On a publicly available stroke prediction dataset, TimberStrike consistently reconstructs between 73.05% and 95.63% of the target dataset across all implementations. We further analyze Differential Privacy, showing that while it partially mitigates the attack, it also significantly degrades model performance. Our findings highlight the need for privacy-preserving mechanisms specifically designed for tree-based Federated Learning systems, and we provide preliminary insights into their design.
Graph Neural Networks (GNNs) achieve high performance across many applications but function as black-box models, limiting their use in critical domains like healthcare and criminal justice. Explainability methods address this by providing feature-level explanations that identify important node attributes for predictions. These explanations create privacy risks. Combined with auxiliary information, feature explanations can enable adversaries to reconstruct graph structure, exposing sensitive relationships. Existing graph reconstruction attacks assume access to original auxiliary data, but practical systems use differential privacy to protect node features and labels while providing explanations for transparency. We study a threat model where adversaries access public feature explanations along with privatized node features and labels. We show that existing explanation-based attacks like GSEF perform poorly with privatized data due to noise from differential privacy mechanisms. We propose ReconXF, a graph reconstruction attack for scenarios with public explanations and privatized auxiliary data. Our method adapts explanation-based frameworks by incorporating denoising mechanisms that handle differential privacy noise while exploiting structural signals in explanations. Experiments across multiple datasets show ReconXF outperforms SoTA methods in privatized settings, with improvements in AUC and average precision. Results indicate that public explanations combined with denoising enable graph structure recovery even under the privacy protection of auxiliary data. Code is available at (link to be made public after acceptance).
Federated Learning (FL) enables collaborative training of machine learning models across distributed clients without sharing raw data, ostensibly preserving data privacy. Nevertheless, recent studies have revealed critical vulnerabilities in FL, showing that a malicious central server can manipulate model updates to reconstruct clients' private training data. Existing data reconstruction attacks have important limitations: they often rely on assumptions about the clients' data distribution or their efficiency significantly degrades when batch sizes exceed just a few tens of samples. In this work, we introduce a novel data reconstruction attack that overcomes these limitations. Our method leverages a new geometric perspective on fully connected layers to craft malicious model parameters, enabling the perfect recovery of arbitrarily large data batches in classification tasks without any prior knowledge of clients' data. Through extensive experiments on both image and tabular datasets, we demonstrate that our attack outperforms existing methods and achieves perfect reconstruction of data batches two orders of magnitude larger than the state of the art.
With the popularity of 3D volumetric video applications, such as Autonomous Driving, Virtual Reality, and Mixed Reality, current developers have turned to deep learning for compressing volumetric video frames, i.e., point clouds for video upstreaming. The latest deep learning-based solutions offer higher efficiency, lower distortion, and better hardware support compared to traditional ones like MPEG and JPEG. However, privacy threats arise, especially reconstruction attacks targeting to recover the original input point cloud from the intermediate results. In this paper, we design VVRec, to the best of our knowledge, which is the first targeting DL-based Volumetric Video Reconstruction attack scheme. VVRec demonstrates the ability to reconstruct high-quality point clouds from intercepted transmission intermediate results using four well-trained neural network modules we design. Leveraging the latest latent diffusion models with Gamma distribution and a refinement algorithm, VVRec excels in reconstruction quality, color recovery, and surpasses existing defenses. We evaluate VVRec using three volumetric video datasets. The results demonstrate that VVRec achieves 64.70dB reconstruction accuracy, with an impressive 46.39% reduction of distortion over baselines.
Reconstruction attacks against federated learning (FL) aim to reconstruct users' samples through users' uploaded gradients. Local differential privacy (LDP) is regarded as an effective defense against various attacks, including sample reconstruction in FL, where gradients are clipped and perturbed. Existing attacks are ineffective in FL with LDP since clipped and perturbed gradients obliterate most sample information for reconstruction. Besides, existing attacks embed additional sample information into gradients to improve the attack effect and cause gradient expansion, leading to a more severe gradient clipping in FL with LDP. In this paper, we propose a sample reconstruction attack against LDP-based FL with any target models to reconstruct victims' sensitive samples to illustrate that FL with LDP is not flawless. Considering gradient expansion in reconstruction attacks and noise in LDP, the core of the proposed attack is gradient compression and reconstructed sample denoising. For gradient compression, an inference structure based on sample characteristics is presented to reduce redundant gradients against LDP. For reconstructed sample denoising, we artificially introduce zero gradients to observe noise distribution and scale confidence interval to filter the noise. Theoretical proof guarantees the effectiveness of the proposed attack. Evaluations show that the proposed attack is the only attack that reconstructs victims' training samples in LDP-based FL and has little impact on the target model's accuracy. We conclude that LDP-based FL needs further improvements to defend against sample reconstruction attacks effectively.
Recent research has shown that machine learning models are vulnerable to privacy attacks targeting their training data. Differential privacy (DP) has become a widely adopted countermeasure, as it offers rigorous privacy protections. In this paper, we introduce a reconstruction attack targeting state-of-the-art $\varepsilon$-DP random forests. By leveraging a constraint programming model that incorporates knowledge of the forest's structure and DP mechanism characteristics, our approach formally reconstructs the most likely dataset that could have produced a given forest. Through extensive computational experiments, we examine the interplay between model utility, privacy guarantees, and reconstruction accuracy across various configurations. Our results reveal that random forests trained with meaningful DP guarantees can still leak substantial portions of their training data. Specifically, while DP reduces the success of reconstruction attacks, the only forests fully robust to our attack exhibit predictive performance no better than a constant classifier. Building on these insights, we provide practical recommendations for the construction of DP random forests that are more resilient to reconstruction attacks and maintain non-trivial predictive performance.
The privacy vulnerabilities of the federated learning (FL) paradigm, primarily caused by gradient leakage, have prompted the development of various defensive measures. Nonetheless, these solutions have predominantly been crafted for and assessed in the context of synchronous FL systems, with minimal focus on asynchronous FL. This gap arises in part due to the unique challenges posed by the asynchronous setting, such as the lack of coordinated updates, increased variability in client participation, and the potential for more severe privacy risks. These concerns have stymied the adoption of asynchronous FL. In this work, we first demonstrate the privacy vulnerabilities of asynchronous FL through a novel data reconstruction attack that exploits gradient updates to recover sensitive client data. To address these vulnerabilities, we propose a privacy-preserving framework that combines a gradient obfuscation mechanism with Trusted Execution Environments (TEEs) for secure asynchronous FL aggregation at the network edge. To overcome the limitations of conventional enclave attestation, we introduce a novel data-centric attestation mechanism based on Multi-Authority Attribute-Based Encryption. This mechanism enables clients to implicitly verify TEE-based aggregation services, effectively handle on-demand client participation, and scale seamlessly with an increasing number of asynchronous connections. Our gradient obfuscation mechanism reduces the structural similarity index of data reconstruction by 85% and increases reconstruction error by 400%, while our framework improves attestation efficiency by lowering average latency by up to 1500% compared to RA-TLS, without additional overhead.
The proliferation of healthcare data has expanded opportunities for collaborative research, yet stringent privacy regulations hinder pooling sensitive patient records. We propose a \emph{multiparty homomorphic encryption-based} framework for \emph{privacy-preserving federated Kaplan--Meier survival analysis}, offering native floating-point support, a theoretical model, and explicit reconstruction-attack mitigation. Compared to prior work, our framework ensures encrypted federated survival estimates closely match centralized outcomes, supported by formal utility-loss bounds that demonstrate convergence as aggregation and decryption noise diminish. Extensive experiments on the NCCTG Lung Cancer and synthetic Breast Cancer datasets confirm low \emph{mean absolute error (MAE)} and \emph{root mean squared error (RMSE)}, indicating negligible deviations between encrypted and non-encrypted survival curves. Log-rank and numerical accuracy tests reveal \emph{no significant difference} between federated encrypted and non-encrypted analyses, preserving statistical validity. A reconstruction-attack evaluation shows smaller federations (2--3 providers) with overlapping data between the institutions are vulnerable, a challenge mitigated by multiparty encryption. Larger federations (5--50 sites) degrade reconstruction accuracy further, with encryption improving confidentiality. Despite an 8--19$\times$ computational overhead, threshold-based homomorphic encryption is \emph{feasible for moderate-scale deployments}, balancing security and runtime. By providing robust privacy guarantees alongside high-fidelity survival estimates, our framework advances the state-of-the art in secure multi-institutional survival analysis.
Federated Learning (FL) emerged as a paradigm for conducting machine learning across broad and decentralized datasets, promising enhanced privacy by obviating the need for direct data sharing. However, recent studies show that attackers can steal private data through model manipulation or gradient analysis. Existing attacks are constrained by low theft quantity or low-resolution data, and they are often detected through anomaly monitoring in gradients or weights. In this paper, we propose a novel data-reconstruction attack leveraging malicious code injection, supported by two key techniques, i.e., distinctive and sparse encoding design and block partitioning. Unlike conventional methods that require detectable changes to the model, our method stealthily embeds a hidden model using parameter sharing to systematically extract sensitive data. The Fibonacci-based index design ensures efficient, structured retrieval of memorized data, while the block partitioning method enhances our method's capability to handle high-resolution images by dividing them into smaller, manageable units. Extensive experiments on 4 datasets confirmed that our method is superior to the five state-of-the-art data-reconstruction attacks under the five respective detection methods. Our method can handle large-scale and high-resolution data without being detected or mitigated by state-of-the-art data reconstruction defense methods. In contrast to baselines, our method can be directly applied to both FedAVG and FedSGD scenarios, underscoring the need for developers to devise new defenses against such vulnerabilities. We will open-source our code upon acceptance.
Face recognition systems extract embedding vectors from face images and use these embeddings to verify or identify individuals. Face reconstruction attack (also known as template inversion) refers to reconstructing face images from face embeddings and using the reconstructed face image to enter a face recognition system. In this paper, we propose to use a face foundation model to reconstruct face images from the embeddings of a blackbox face recognition model. The foundation model is trained with 42M images to generate face images from the facial embeddings of a fixed face recognition model. We propose to use an adapter to translate target embeddings into the embedding space of the foundation model. The generated images are evaluated on different face recognition models and different datasets, demonstrating the effectiveness of our method to translate embeddings of different face recognition models. We also evaluate the transferability of reconstructed face images when attacking different face recognition models. Our experimental results show that our reconstructed face images outperform previous reconstruction attacks against face recognition models.
This study investigates privacy leakage in dimensionality reduction methods through a novel machine learning-based reconstruction attack. Employing an informed adversary threat model, we develop a neural network capable of reconstructing high-dimensional data from low-dimensional embeddings. We evaluate six popular dimensionality reduction techniques: principal component analysis (PCA), sparse random projection (SRP), multidimensional scaling (MDS), Isomap, $t$-distributed stochastic neighbor embedding ($t$-SNE), and uniform manifold approximation and projection (UMAP). Using both MNIST and NIH Chest X-ray datasets, we perform a qualitative analysis to identify key factors affecting reconstruction quality. Furthermore, we assess the effectiveness of an additive noise mechanism in mitigating these reconstruction attacks. Our experimental results on both datasets reveal that the attack is effective against deterministic methods (PCA and Isomap). but ineffective against methods that employ random initialization (SRP, MDS, $t$-SNE and UMAP). The experimental results also show that, for PCA and Isomap, our reconstruction network produces higher quality outputs compared to a previously proposed network. We also study the effect of additive noise mechanism to prevent the reconstruction attack. Our experiment shows that, when adding the images with large noises before performing PCA or Isomap, the attack produced severely distorted reconstructions. In contrast, for the other four methods, the reconstructions still show some recognizable features, though they bear little resemblance to the original images. The code is available at https://github.com/Chayadon/Reconstruction_attack_on_DR
Biometric recognition systems are security systems based on intrinsic properties of their users, usually encoded in high dimension representations called embeddings, which potential theft would represent a greater threat than a temporary password or a replaceable key. To study the threat of embedding theft, we perform spoofing attacks on two behavioral biometric systems (an automatic speaker verification system and a handwritten digit analysis system) using a set of alignment techniques. Biometric recognition systems based on embeddings work in two phases: enrollment - where embeddings are collected and stored - then authentication - when new embeddings are compared to the stored ones -.The threat of stolen enrollment embeddings has been explored by the template reconstruction attack literature: reconstructing the original data to spoof an authentication system is doable with black-box access to their encoder. In this document, we explore the options available to perform template reconstruction attacks without any access to the encoder. To perform those attacks, we suppose general rules over the distribution of embeddings across encoders and use supervised and unsupervised algorithms to align an unlabeled set of embeddings with a set from a known encoder. The use of an alignment algorithm from the unsupervised translation literature gives promising results on spoofing two behavioral biometric systems.
This paper investigates the security vulnerabilities of adversarial-example-based image encryption by executing data reconstruction (DR) attacks on encrypted images. A representative image encryption method is the adversarial visual information hiding (AVIH), which uses type-I adversarial example training to protect gallery datasets used in image recognition tasks. In the AVIH method, the type-I adversarial example approach creates images that appear completely different but are still recognized by machines as the original ones. Additionally, the AVIH method can restore encrypted images to their original forms using a predefined private key generative model. For the best security, assigning a unique key to each image is recommended; however, storage limitations may necessitate some images sharing the same key model. This raises a crucial security question for AVIH: How many images can safely share the same key model without being compromised by a DR attack? To address this question, we introduce a dual-strategy DR attack against the AVIH encryption method by incorporating (1) generative-adversarial loss and (2) augmented identity loss, which prevent DR from overfitting -- an issue akin to that in machine learning. Our numerical results validate this approach through image recognition and re-identification benchmarks, demonstrating that our strategy can significantly enhance the quality of reconstructed images, thereby requiring fewer key-sharing encrypted images. Our source code to reproduce our results will be available soon.
Understanding the vulnerability of face recognition systems to malicious attacks is of critical importance. Previous works have focused on reconstructing face images that can penetrate a targeted verification system. Even in the white-box scenario, however, naively reconstructed images misrepresent the identity information, hence the attacks are easily neutralized once the face system is updated or changed. In this paper, we aim to reconstruct face images which are capable of transferring face attacks on unseen encoders. We term this problem as Face Reconstruction Transfer Attack (FRTA) and show that it can be formulated as an out-of-distribution (OOD) generalization problem. Inspired by its OOD nature, we propose to solve FRTA by Averaged Latent Search and Unsupervised Validation with pseudo target (ALSUV). To strengthen the reconstruction attack on OOD unseen encoders, ALSUV reconstructs the face by searching the latent of amortized generator StyleGAN2 through multiple latent optimization, latent optimization trajectory averaging, and unsupervised validation with a pseudo target. We demonstrate the efficacy and generalization of our method on widely used face datasets, accompanying it with extensive ablation studies and visually, qualitatively, and quantitatively analyses. The source code will be released.
Within the machine learning community, reconstruction attacks are a principal attack of concern and have been identified even in federated learning, which was designed with privacy preservation in mind. In federated learning, it has been shown that an adversary with knowledge of the machine learning architecture is able to infer the exact value of a training element given an observation of the weight updates performed during stochastic gradient descent. In response to these threats, the privacy community recommends the use of differential privacy in the stochastic gradient descent algorithm, termed DP-SGD. However, DP has not yet been formally established as an effective countermeasure against reconstruction attacks. In this paper, we formalise the reconstruction threat model using the information-theoretic framework of quantitative information flow. We show that the Bayes' capacity, related to the Sibson mutual information of order infinity, represents a tight upper bound on the leakage of the DP-SGD algorithm to an adversary interested in performing a reconstruction attack. We provide empirical results demonstrating the effectiveness of this measure for comparing mechanisms against reconstruction threats.
Vertical Federated Learning (VFL) facilitates collaborative machine learning without the need for participants to share raw private data. However, recent studies have revealed privacy risks where adversaries might reconstruct sensitive features through data leakage during the learning process. Although data reconstruction methods based on gradient or model information are somewhat effective, they reveal limitations in VFL application scenarios. This is because these traditional methods heavily rely on specific model structures and/or have strict limitations on application scenarios. To address this, our study introduces the Unified InverNet Framework into VFL, which yields a novel and flexible approach (dubbed UIFV) that leverages intermediate feature data to reconstruct original data, instead of relying on gradients or model details. The intermediate feature data is the feature exchanged by different participants during the inference phase of VFL. Experiments on four datasets demonstrate that our methods significantly outperform state-of-the-art techniques in attack precision. Our work exposes severe privacy vulnerabilities within VFL systems that pose real threats to practical VFL applications and thus confirms the necessity of further enhancing privacy protection in the VFL architecture.
Gradient leakage has been identified as a potential source of privacy breaches in modern image processing systems, where the adversary can completely reconstruct the training images from leaked gradients. However, existing methods are restricted to reconstructing low-resolution images where data leakage risks of image processing systems are not sufficiently explored. In this paper, by exploiting diffusion models, we propose an innovative gradient-guided fine-tuning method and introduce a new reconstruction attack that is capable of stealing private, high-resolution images from image processing systems through leaked gradients where severe data leakage encounters. Our attack method is easy to implement and requires little prior knowledge. The experimental results indicate that current reconstruction attacks can steal images only up to a resolution of $128 \times 128$ pixels, while our attack method can successfully recover and steal images with resolutions up to $512 \times 512$ pixels. Our attack method significantly outperforms the SOTA attack baselines in terms of both pixel-wise accuracy and time efficiency of image reconstruction. Furthermore, our attack can render differential privacy ineffective to some extent.
Launching effective malicious attacks in VFL presents unique challenges: 1) Firstly, given the distributed nature of clients' data features and models, each client rigorously guards its privacy and prohibits direct querying, complicating any attempts to steal data; 2) Existing malicious attacks alter the underlying VFL training task, and are hence easily detected by comparing the received gradients with the ones received in honest training. To overcome these challenges, we develop URVFL, a novel attack strategy that evades current detection mechanisms. The key idea is to integrate a discriminator with auxiliary classifier that takes a full advantage of the label information and generates malicious gradients to the victim clients: on one hand, label information helps to better characterize embeddings of samples from distinct classes, yielding an improved reconstruction performance; on the other hand, computing malicious gradients with label information better mimics the honest training, making the malicious gradients indistinguishable from the honest ones, and the attack much more stealthy. Our comprehensive experiments demonstrate that URVFL significantly outperforms existing attacks, and successfully circumvents SOTA detection methods for malicious attacks. Additional ablation studies and evaluations on defenses further underscore the robustness and effectiveness of URVFL. Our code will be available at https://github.com/duanyiyao/URVFL.