Quantum Machine Learning (QML) systems inherit vulnerabilities from classical machine learning while introducing new attack surfaces rooted in the physical and algorithmic layers of quantum computing. Despite a growing body of research on individual attack vectors - ranging from adversarial poisoning and evasion to circuit-level backdoors, side-channel leakage, and model extraction - these threats are often analyzed in isolation, with unrealistic assumptions about attacker capabilities and system environments. This fragmentation hampers the development of effective, holistic defense strategies. In this work, we argue that QML security requires more structured modeling of the attack surface, capturing not only individual techniques but also their relationships, prerequisites, and potential impact across the QML pipeline. We propose adapting kill chain models, widely used in classical IT and cybersecurity, to the quantum machine learning context. Such models allow for structured reasoning about attacker objectives, capabilities, and possible multi-stage attack paths - spanning reconnaissance, initial access, manipulation, persistence, and exfiltration. Based on extensive literature analysis, we present a detailed taxonomy of QML attack vectors mapped to corresponding stages in a quantum-aware kill chain framework that is inspired by the MITRE ATLAS for classical machine learning. We highlight interdependencies between physical-level threats (like side-channel leakage and crosstalk faults), data and algorithm manipulation (such as poisoning or circuit backdoors), and privacy attacks (including model extraction and training data inference). This work provides a foundation for more realistic threat modeling and proactive security-in-depth design in the emerging field of quantum machine learning.
Neural network model extraction has emerged in recent years as an important security concern, as adversaries attempt to recover a network's parameters via black-box queries. A key step in this process is signature extraction, which aims to recover the absolute values of the network's weights layer by layer. Prior work, notably by Carlini et al. (2020), introduced a technique inspired by differential cryptanalysis to extract neural network parameters. However, their method suffers from several limitations that restrict its applicability to networks with a few layers only. Later works focused on improving sign extraction, but largely relied on the assumption that signature extraction itself was feasible. In this work, we revisit and refine the signature extraction process by systematically identifying and addressing for the first time critical limitations of Carlini et al.'s signature extraction method. These limitations include rank deficiency and noise propagation from deeper layers. To overcome these challenges, we propose efficient algorithmic solutions for each of the identified issues, greatly improving the efficiency of signature extraction. Our approach permits the extraction of much deeper networks than was previously possible. We validate our method through extensive experiments on ReLU-based neural networks, demonstrating significant improvements in extraction depth and accuracy. For instance, our extracted network matches the target network on at least 95% of the input space for each of the eight layers of a neural network trained on the CIFAR-10 dataset, while previous works could barely extract the first three layers. Our results represent a crucial step toward practical attacks on larger and more complex neural network architectures.
Graph Neural Networks (GNNs) have demonstrated remarkable utility across diverse applications, and their growing complexity has made Machine Learning as a Service (MLaaS) a viable platform for scalable deployment. However, this accessibility also exposes GNN to serious security threats, most notably model extraction attacks (MEAs), in which adversaries strategically query a deployed model to construct a high-fidelity replica. In this work, we evaluate the vulnerability of GNNs to MEAs and explore their potential for cost-effective model acquisition in non-adversarial research settings. Importantly, adaptive node querying strategies can also serve a critical role in research, particularly when labeling data is expensive or time-consuming. By selectively sampling informative nodes, researchers can train high-performing GNNs with minimal supervision, which is particularly valuable in domains such as biomedicine, where annotations often require expert input. To address this, we propose a node querying strategy tailored to a highly practical yet underexplored scenario, where bulk queries are prohibited, and only a limited set of initial nodes is available. Our approach iteratively refines the node selection mechanism over multiple learning cycles, leveraging historical feedback to improve extraction efficiency. Extensive experiments on benchmark graph datasets demonstrate our superiority over comparable baselines on accuracy, fidelity, and F1 score under strict query-size constraints. These results highlight both the susceptibility of deployed GNNs to extraction attacks and the promise of ethical, efficient GNN acquisition methods to support low-resource research environments.
Recent advancements in diffusion models have enabled high-fidelity and photorealistic image generation across diverse applications. However, these models also present security and privacy risks, including copyright violations, sensitive information leakage, and the creation of harmful or offensive content that could be exploited maliciously. In this study, we uncover a novel security threat where an attacker leverages diffusion model APIs to generate synthetic images, which are then used to train a high-performing substitute model. This enables the attacker to execute model extraction and transfer-based adversarial attacks on black-box classification models with minimal queries, without needing access to the original training data. The generated images are sufficiently high-resolution and diverse to train a substitute model whose outputs closely match those of the target model. Across the seven benchmarks, including CIFAR and ImageNet subsets, our method shows an average improvement of 27.37% over state-of-the-art methods while using just 0.01 times of the query budget, achieving a 98.68% success rate in adversarial attacks on the target model.
In this paper, we introduce GradEscape, the first gradient-based evader designed to attack AI-generated text (AIGT) detectors. GradEscape overcomes the undifferentiable computation problem, caused by the discrete nature of text, by introducing a novel approach to construct weighted embeddings for the detector input. It then updates the evader model parameters using feedback from victim detectors, achieving high attack success with minimal text modification. To address the issue of tokenizer mismatch between the evader and the detector, we introduce a warm-started evader method, enabling GradEscape to adapt to detectors across any language model architecture. Moreover, we employ novel tokenizer inference and model extraction techniques, facilitating effective evasion even in query-only access. We evaluate GradEscape on four datasets and three widely-used language models, benchmarking it against four state-of-the-art AIGT evaders. Experimental results demonstrate that GradEscape outperforms existing evaders in various scenarios, including with an 11B paraphrase model, while utilizing only 139M parameters. We have successfully applied GradEscape to two real-world commercial AIGT detectors. Our analysis reveals that the primary vulnerability stems from disparity in text expression styles within the training data. We also propose a potential defense strategy to mitigate the threat of AIGT evaders. We open-source our GradEscape for developing more robust AIGT detectors.
Model extraction attacks aim to replicate the functionality of a black-box model through query access, threatening the intellectual property (IP) of machine-learning-as-a-service (MLaaS) providers. Defending against such attacks is challenging, as it must balance efficiency, robustness, and utility preservation in the real-world scenario. Despite the recent advances, most existing defenses presume that attacker queries have out-of-distribution (OOD) samples, enabling them to detect and disrupt suspicious inputs. However, this assumption is increasingly unreliable, as modern models are trained on diverse datasets and attackers often operate under limited query budgets. As a result, the effectiveness of these defenses is significantly compromised in realistic deployment scenarios. To address this gap, we propose MISLEADER (enseMbles of dIStiLled modEls Against moDel ExtRaction), a novel defense strategy that does not rely on OOD assumptions. MISLEADER formulates model protection as a bilevel optimization problem that simultaneously preserves predictive fidelity on benign inputs and reduces extractability by potential clone models. Our framework combines data augmentation to simulate attacker queries with an ensemble of heterogeneous distilled models to improve robustness and diversity. We further provide a tractable approximation algorithm and derive theoretical error bounds to characterize defense effectiveness. Extensive experiments across various settings validate the utility-preserving and extraction-resistant properties of our proposed defense strategy. Our code is available at https://github.com/LabRAI/MISLEADER.
Federated Learning (FL) is a collaborative learning framework designed to protect client data, yet it remains highly vulnerable to Intellectual Property (IP) threats. Model extraction (ME) attacks pose a significant risk to Machine Learning as a Service (MLaaS) platforms, enabling attackers to replicate confidential models by querying black-box (without internal insight) APIs. Despite FL's privacy-preserving goals, its distributed nature makes it particularly susceptible to such attacks. This paper examines the vulnerability of FL-based victim models to two types of model extraction attacks. For various federated clients built under the NVFlare platform, we implemented ME attacks across two deep learning architectures and three image datasets. We evaluate the proposed ME attack performance using various metrics, including accuracy, fidelity, and KL divergence. The experiments show that for different FL clients, the accuracy and fidelity of the extracted model are closely related to the size of the attack query set. Additionally, we explore a transfer learning based approach where pretrained models serve as the starting point for the extraction process. The results indicate that the accuracy and fidelity of the fine-tuned pretrained extraction models are notably higher, particularly with smaller query sets, highlighting potential advantages for attackers.
Machine Learning as a Service (MLaaS) has gained important attraction as a means for deploying powerful predictive models, offering ease of use that enables organizations to leverage advanced analytics without substantial investments in specialized infrastructure or expertise. However, MLaaS platforms must be safeguarded against security and privacy attacks, such as model extraction (MEA) attacks. The increasing integration of explainable AI (XAI) within MLaaS has introduced an additional privacy challenge, as attackers can exploit model explanations particularly counterfactual explanations (CFs) to facilitate MEA. In this paper, we investigate the trade offs among model performance, privacy, and explainability when employing Differential Privacy (DP), a promising technique for mitigating CF facilitated MEA. We evaluate two distinct DP strategies: implemented during the classification model training and at the explainer during CF generation.
Reinforcement learning (RL) agents have shown remarkable performances in various environments, where they can discover effective policies directly from sensory inputs. However, these agents often exploit spurious correlations in the training data, resulting in brittle behaviours that fail to generalize to new or slightly modified environments. To address this, we introduce the Causal Object-centric Model Extraction Tool (COMET), a novel algorithm designed to learn the exact interpretable causal world models (CWMs). COMET first extracts object-centric state descriptions from observations and identifies the environment's internal states related to the depicted objects' properties. Using symbolic regression, it models object-centric transitions and derives causal relationships governing object dynamics. COMET further incorporates large language models (LLMs) for semantic inference, annotating causal variables to enhance interpretability. By leveraging these capabilities, COMET constructs CWMs that align with the true causal structure of the environment, enabling agents to focus on task-relevant features. The extracted CWMs mitigate the danger of shortcuts, permitting the development of RL systems capable of better planning and decision-making across dynamic scenarios. Our results, validated in Atari environments such as Pong and Freeway, demonstrate the accuracy and robustness of COMET, highlighting its potential to bridge the gap between object-centric reasoning and causal inference in reinforcement learning.
Quantum Neural Networks (QNNs) have shown significant value across domains, with well-trained QNNs representing critical intellectual property often deployed via cloud-based QNN-as-a-Service (QNNaaS) platforms. Recent work has examined QNN model extraction attacks using classical and emerging quantum strategies. These attacks involve adversaries querying QNNaaS platforms to obtain labeled data for training local substitute QNNs that replicate the functionality of cloud-based models. However, existing approaches have largely overlooked the impact of varying quantum noise inherent in noisy intermediate-scale quantum (NISQ) computers, limiting their effectiveness in real-world settings. To address this limitation, we propose the CopyQNN framework, which employs a three-step data cleaning method to eliminate noisy data based on its noise sensitivity. This is followed by the integration of contrastive and transfer learning within the quantum domain, enabling efficient training of substitute QNNs using a limited but cleaned set of queried data. Experimental results on NISQ computers demonstrate that a practical implementation of CopyQNN significantly outperforms state-of-the-art QNN extraction attacks, achieving an average performance improvement of 8.73% across all tasks while reducing the number of required queries by 90x, with only a modest increase in hardware overhead.
Graph Neural Networks (GNNs) have gained traction in Graph-based Machine Learning as a Service (GMLaaS) platforms, yet they remain vulnerable to graph-based model extraction attacks (MEAs), where adversaries reconstruct surrogate models by querying the victim model. Existing defense mechanisms, such as watermarking and fingerprinting, suffer from poor real-time performance, susceptibility to evasion, or reliance on post-attack verification, making them inadequate for handling the dynamic characteristics of graph-based MEA variants. To address these limitations, we propose ATOM, a novel real-time MEA detection framework tailored for GNNs. ATOM integrates sequential modeling and reinforcement learning to dynamically detect evolving attack patterns, while leveraging $k$-core embedding to capture the structural properties, enhancing detection precision. Furthermore, we provide theoretical analysis to characterize query behaviors and optimize detection strategies. Extensive experiments on multiple real-world datasets demonstrate that ATOM outperforms existing approaches in detection performance, maintaining stable across different time steps, thereby offering a more effective defense mechanism for GMLaaS environments.
Pre-trained models are valuable intellectual property, capturing both domain-specific and domain-invariant features within their weight spaces. However, model extraction attacks threaten these assets by enabling unauthorized source-domain inference and facilitating cross-domain transfer via the exploitation of domain-invariant features. In this work, we introduce **ProDiF**, a novel framework that leverages targeted weight space manipulation to secure pre-trained models against extraction attacks. **ProDiF** quantifies the transferability of filters and perturbs the weights of critical filters in unsecured memory, while preserving actual critical weights in a Trusted Execution Environment (TEE) for authorized users. A bi-level optimization further ensures resilience against adaptive fine-tuning attacks. Experimental results show that **ProDiF** reduces source-domain accuracy to near-random levels and decreases cross-domain transferability by 74.65\%, providing robust protection for pre-trained models. This work offers comprehensive protection for pre-trained DNN models and highlights the potential of weight space manipulation as a novel approach to model security.
Model Extraction Attacks (MEAs) threaten modern machine learning systems by enabling adversaries to steal models, exposing intellectual property and training data. With the increasing deployment of machine learning models in distributed computing environments, including cloud, edge, and federated learning settings, each paradigm introduces distinct vulnerabilities and challenges. Without a unified perspective on MEAs across these distributed environments, organizations risk fragmented defenses, inadequate risk assessments, and substantial economic and privacy losses. This survey is motivated by the urgent need to understand how the unique characteristics of cloud, edge, and federated deployments shape attack vectors and defense requirements. We systematically examine the evolution of attack methodologies and defense mechanisms across these environments, demonstrating how environmental factors influence security strategies in critical sectors such as autonomous vehicles, healthcare, and financial services. By synthesizing recent advances in MEAs research and discussing the limitations of current evaluation practices, this survey provides essential insights for developing robust and adaptive defense strategies. Our comprehensive approach highlights the importance of integrating protective measures across the entire distributed computing landscape to ensure the secure deployment of machine learning models.
Based on global genomic status, the cancer tumor is classified as Microsatellite Instable (MSI) and Microsatellite Stable (MSS). Immunotherapy is used to diagnose MSI, whereas radiation and chemotherapy are used for MSS. Therefore, it is significant to classify a gastro-intestinal (GI) cancer tumor into MSI vs. MSS to provide appropriate treatment. The existing literature showed that deep learning could directly predict the class of GI cancer tumors from histological images. However, deep learning (DL) models are susceptible to various threats, including membership inference attacks, model extraction attacks, etc. These attacks render the use of DL models impractical in real-world scenarios. To make the DL models useful and maintain privacy, we integrate differential privacy (DP) with DL. In particular, this paper aims to predict the state of GI cancer while preserving the privacy of sensitive data. We fine-tuned the Normalizer Free Net (NF-Net) model. We obtained an accuracy of 88.98\% without DP to predict (GI) cancer status. When we fine-tuned the NF-Net using DP-AdamW and adaptive DP-AdamW, we got accuracies of 74.58% and 76.48%, respectively. Moreover, we investigate the Weighted Random Sampler (WRS) and Class weighting (CW) to solve the data imbalance. We also evaluated and analyzed the DP algorithms in different settings.
The advent of Machine Learning as a Service (MLaaS) has heightened the trade-off between model explainability and security. In particular, explainability techniques, such as counterfactual explanations, inadvertently increase the risk of model extraction attacks, enabling unauthorized replication of proprietary models. In this paper, we formalize and characterize the risks and inherent complexity of model reconstruction, focusing on the "oracle'' queries required for faithfully inferring the underlying prediction function. We present the first formal analysis of model extraction attacks through the lens of competitive analysis, establishing a foundational framework to evaluate their efficiency. Focusing on models based on additive decision trees (e.g., decision trees, gradient boosting, and random forests), we introduce novel reconstruction algorithms that achieve provably perfect fidelity while demonstrating strong anytime performance. Our framework provides theoretical bounds on the query complexity for extracting tree-based model, offering new insights into the security vulnerabilities of their deployment.
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a wide range of applications, including conversational AI, recommendation systems, autonomous driving, content generation, medical diagnostics, and scientific discovery. However, their widespread deployment also exposes them to significant safety risks, raising concerns about robustness, reliability, and ethical implications. This survey provides a systematic review of current safety research on large models, covering Vision Foundation Models (VFMs), Large Language Models (LLMs), Vision-Language Pre-training (VLP) models, Vision-Language Models (VLMs), Diffusion Models (DMs), and large-model-based Agents. Our contributions are summarized as follows: (1) We present a comprehensive taxonomy of safety threats to these models, including adversarial attacks, data poisoning, backdoor attacks, jailbreak and prompt injection attacks, energy-latency attacks, data and model extraction attacks, and emerging agent-specific threats. (2) We review defense strategies proposed for each type of attacks if available and summarize the commonly used datasets and benchmarks for safety research. (3) Building on this, we identify and discuss the open challenges in large model safety, emphasizing the need for comprehensive safety evaluations, scalable and effective defense mechanisms, and sustainable data practices. More importantly, we highlight the necessity of collective efforts from the research community and international collaboration. Our work can serve as a useful reference for researchers and practitioners, fostering the ongoing development of comprehensive defense systems and platforms to safeguard AI models.
The availability of foundational models (FMs) pre-trained on large-scale data has advanced the state-of-the-art in many computer vision tasks. While FMs have demonstrated good zero-shot performance on many image classification tasks, there is often scope for performance improvement by adapting the FM to the downstream task. However, the data that is required for this adaptation typically exists in silos across multiple entities (data owners) and cannot be collated at a central location due to regulations and privacy concerns. At the same time, a learning service provider (LSP) who owns the FM cannot share the model with the data owners due to proprietary reasons. In some cases, the data owners may not even have the resources to store such large FMs. Hence, there is a need for algorithms to adapt the FM in a double-blind federated manner, i.e., the data owners do not know the FM or each other's data, and the LSP does not see the data for the downstream tasks. In this work, we propose a framework for double-blind federated adaptation of FMs using fully homomorphic encryption (FHE). The proposed framework first decomposes the FM into a sequence of FHE-friendly blocks through knowledge distillation. The resulting FHE-friendly model is adapted for the downstream task via low-rank parallel adapters that can be learned without backpropagation through the FM. Since the proposed framework requires the LSP to share intermediate representations with the data owners, we design a privacy-preserving permutation scheme to prevent the data owners from learning the FM through model extraction attacks. Finally, a secure aggregation protocol is employed for federated learning of the low-rank parallel adapters. Empirical results on four datasets demonstrate the practical feasibility of the proposed framework.
Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While existing research on adversarial applications of generative AI predominantly focuses on cyberattacks, less attention has been given to attacks targeting deep learning models. In this paper, we introduce the use of generative AI for facilitating model-related attacks, including model extraction, membership inference, and model inversion. Our study reveals that adversaries can launch a variety of model-related attacks against both image and text models in a data-free and black-box manner, achieving comparable performance to baseline methods that have access to the target models' training data and parameters in a white-box manner. This research serves as an important early warning to the community about the potential risks associated with generative AI-powered attacks on deep learning models.
Feature selection is a crucial preprocessing step in machine learning, impacting model performance, interpretability, and computational efficiency. This study introduces a novel hybrid approach, the Forward Recursive Adaptive Model Extraction Technique (FRAME), which combines Forward Selection and Recursive Feature Elimination (RFE) to enhance feature selection across diverse datasets. FRAME integrates the strengths of both methods, balancing exploration and exploitation of features to optimize selection. A comprehensive evaluation of FRAME was conducted against traditional methods such as SelectKBest and Lasso Regression, using high-dimensional, noisy, and heterogeneous datasets. The results demonstrate that FRAME consistently delivers superior predictive performance based on downstream machine learning evaluation metrics. It effectively reduces dimensionality while maintaining robust model performance, making it particularly valuable for applications requiring interpretable and accurate predictions, such as biomedical diagnostics. This study highlights the importance of assessing feature selection methods across varied datasets to ensure their robustness and generalizability. The findings suggest that FRAME has significant potential for further enhancement, particularly through integration with deep learning architectures for adaptive and real-time feature selection in dynamic environments. By advancing feature selection methodologies, FRAME offers a practical and effective solution to improve machine learning applications across multiple domains.
Developing high-performance deep learning models is resource-intensive, leading model owners to utilize Machine Learning as a Service (MLaaS) platforms instead of publicly releasing their models. However, malicious users may exploit query interfaces to execute model extraction attacks, reconstructing the target model's functionality locally. While prior research has investigated triggerable watermarking techniques for asserting ownership, existing methods face significant challenges: (1) most approaches require additional training, resulting in high overhead and limited flexibility, and (2) they often fail to account for advanced attackers, leaving them vulnerable to adaptive attacks. In this paper, we propose Neural Honeytrace, a robust plug-and-play watermarking framework against model extraction attacks. We first formulate a watermark transmission model from an information-theoretic perspective, providing an interpretable account of the principles and limitations of existing triggerable watermarking. Guided by the model, we further introduce: (1) a similarity-based training-free watermarking method for plug-and-play and flexible watermarking, and (2) a distribution-based multi-step watermark information transmission strategy for robust watermarking. Comprehensive experiments on four datasets demonstrate that Neural Honeytrace outperforms previous methods in efficiency and resisting adaptive attacks. Neural Honeytrace reduces the average number of samples required for a worst-case t-Test-based copyright claim from 193,252 to 1,857 with zero training cost. The code is available at https://github.com/NeurHT/NeurHT.