New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook

Thanks to the explosive growth of data and the development of computational resources, it is possible to build pre-trained models that can achieve outstanding performance on various tasks, such as neural language processing, computer vision, and more. Despite their powerful capabilities, pre-trained models have also sparked attention to the emerging security challenges associated with their real-world applications. Security and privacy issues, such as leaking privacy information and generating harmful responses, have seriously undermined users' confidence in these powerful models. Concerns are growing as model performance improves dramatically. Researchers are eager to explore the unique security and privacy issues that have emerged, their distinguishing factors, and how to defend against them. However, the current literature lacks a clear taxonomy of emerging attacks and defenses for pre-trained models, which hinders a high-level and comprehensive understanding of these questions. To fill the gap, we conduct a systematical survey on the security risks of pre-trained models, proposing a taxonomy of attack and defense methods based on the accessibility of pre-trained models' input and weights in various security test scenarios. This taxonomy categorizes attacks and defenses into No-Change, Input-Change, and Model-Change approaches. With the taxonomy analysis, we capture the unique security and privacy issues of pre-trained models, categorizing and summarizing existing security issues based on their characteristics. In addition, we offer a timely and comprehensive review of each category's strengths and limitations. Our survey concludes by highlighting potential new research opportunities in the security and privacy of pre-trained models.

Game-Theoretic Machine Unlearning: Mitigating Extra Privacy Leakage

With the extensive use of machine learning technologies, data providers encounter increasing privacy risks. Recent legislation, such as GDPR, obligates organizations to remove requested data and its influence from a trained model. Machine unlearning is an emerging technique designed to enable machine learning models to erase users' private information. Although several efficient machine unlearning schemes have been proposed, these methods still have limitations. First, removing the contributions of partial data may lead to model performance degradation. Second, discrepancies between the original and generated unlearned models can be exploited by attackers to obtain target sample's information, resulting in additional privacy leakage risks. To address above challenges, we proposed a game-theoretic machine unlearning algorithm that simulates the competitive relationship between unlearning performance and privacy protection. This algorithm comprises unlearning and privacy modules. The unlearning module possesses a loss function composed of model distance and classification error, which is used to derive the optimal strategy. The privacy module aims to make it difficult for an attacker to infer membership information from the unlearned data, thereby reducing the privacy leakage risk during the unlearning process. Additionally, the experimental results on real-world datasets demonstrate that this game-theoretic unlearning algorithm's effectiveness and its ability to generate an unlearned model with a performance similar to that of the retrained one while mitigating extra privacy leakage risks.

Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation

In the rapid advancement of artificial intelligence, privacy protection has become crucial, giving rise to machine unlearning. Machine unlearning is a technique that removes specific data influences from trained models without the need for extensive retraining. However, it faces several key challenges, including accurately implementing unlearning, ensuring privacy protection during the unlearning process, and achieving effective unlearning without significantly compromising model performance. This paper presents a novel approach to machine unlearning by employing Layer-wise Relevance Analysis and Neuronal Path Perturbation. We address three primary challenges: the lack of detailed unlearning principles, privacy guarantees in zero-shot unlearning scenario, and the balance between unlearning effectiveness and model utility. Our method balances machine unlearning performance and model utility by identifying and perturbing highly relevant neurons, thereby achieving effective unlearning. By using data not present in the original training set during the unlearning process, we satisfy the zero-shot unlearning scenario and ensure robust privacy protection. Experimental results demonstrate that our approach effectively removes targeted data from the target unlearning model while maintaining the model's utility, offering a practical solution for privacy-preserving machine learning.

When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?

The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently learn and retain sensitive information and harmful content during training, raising significant ethical and legal concerns. To address these issues, machine unlearning has been introduced as a potential solution. While existing unlearning methods take into account the specific characteristics of LLMs, they often suffer from high computational demands, limited applicability, or the risk of catastrophic forgetting. To address these limitations, we propose a lightweight unlearning framework based on Retrieval-Augmented Generation (RAG) technology. By modifying the external knowledge base of RAG, we simulate the effects of forgetting without directly interacting with the unlearned LLM. We approach the construction of unlearned knowledge as a constrained optimization problem, deriving two key components that underpin the effectiveness of RAG-based unlearning. This RAG-based approach is particularly effective for closed-source LLMs, where existing unlearning methods often fail. We evaluate our framework through extensive experiments on both open-source and closed-source models, including ChatGPT, Gemini, Llama-2-7b-chat-hf, and PaLM 2. The results demonstrate that our approach meets five key unlearning criteria: effectiveness, universality, harmlessness, simplicity, and robustness. Meanwhile, this approach can extend to multimodal large language models and LLM-based agents.

Query-Efficient Video Adversarial Attack with Stylized Logo

Video classification systems based on Deep Neural Networks (DNNs) have demonstrated excellent performance in accurately verifying video content. However, recent studies have shown that DNNs are highly vulnerable to adversarial examples. Therefore, a deep understanding of adversarial attacks can better respond to emergency situations. In order to improve attack performance, many style-transfer-based attacks and patch-based attacks have been proposed. However, the global perturbation of the former will bring unnatural global color, while the latter is difficult to achieve success in targeted attacks due to the limited perturbation space. Moreover, compared to a plethora of methods targeting image classifiers, video adversarial attacks are still not that popular. Therefore, to generate adversarial examples with a low budget and to provide them with a higher verisimilitude, we propose a novel black-box video attack framework, called Stylized Logo Attack (SLA). SLA is conducted through three steps. The first step involves building a style references set for logos, which can not only make the generated examples more natural, but also carry more target class features in the targeted attacks. Then, reinforcement learning (RL) is employed to determine the style reference and position parameters of the logo within the video, which ensures that the stylized logo is placed in the video with optimal attributes. Finally, perturbation optimization is designed to optimize perturbations to improve the fooling rate in a step-by-step manner. Sufficient experimental results indicate that, SLA can achieve better performance than state-of-the-art methods and still maintain good deception effects when facing various defense methods.

DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction

Self-driving industries usually employ professional artists to build exquisite 3D cars. However, it is expensive to craft large-scale digital assets. Since there are already numerous datasets available that contain a vast number of images of cars, we focus on reconstructing high-quality 3D car models from these datasets. However, these datasets only contain one side of cars in the forward-moving scene. We try to use the existing generative models to provide more supervision information, but they struggle to generalize well in cars since they are trained on synthetic datasets not car-specific. In addition, The reconstructed 3D car texture misaligns due to a large error in camera pose estimation when dealing with in-the-wild images. These restrictions make it challenging for previous methods to reconstruct complete 3D cars. To address these problems, we propose a novel method, named DreamCar, which can reconstruct high-quality 3D cars given a few images even a single image. To generalize the generative model, we collect a car dataset, named Car360, with over 5,600 vehicles. With this dataset, we make the generative model more robust to cars. We use this generative prior specific to the car to guide its reconstruction via Score Distillation Sampling. To further complement the supervision information, we utilize the geometric and appearance symmetry of cars. Finally, we propose a pose optimization method that rectifies poses to tackle texture misalignment. Extensive experiments demonstrate that our method significantly outperforms existing methods in reconstructing high-quality 3D cars. \href{https://xiaobiaodu.github.io/dreamcar-project/}{Our code is available.}

QUEEN: Query Unlearning against Model Extraction

Model extraction attacks currently pose a non-negligible threat to the security and privacy of deep learning models. By querying the model with a small dataset and usingthe query results as the ground-truth labels, an adversary can steal a piracy model with performance comparable to the original model. Two key issues that cause the threat are, on the one hand, accurate and unlimited queries can be obtained by the adversary; on the other hand, the adversary can aggregate the query results to train the model step by step. The existing defenses usually employ model watermarking or fingerprinting to protect the ownership. However, these methods cannot proactively prevent the violation from happening. To mitigate the threat, we propose QUEEN (QUEry unlEarNing) that proactively launches counterattacks on potential model extraction attacks from the very beginning. To limit the potential threat, QUEEN has sensitivity measurement and outputs perturbation that prevents the adversary from training a piracy model with high performance. In sensitivity measurement, QUEEN measures the single query sensitivity by its distance from the center of its cluster in the feature space. To reduce the learning accuracy of attacks, for the highly sensitive query batch, QUEEN applies query unlearning, which is implemented by gradient reverse to perturb the softmax output such that the piracy model will generate reverse gradients to worsen its performance unconsciously. Experiments show that QUEEN outperforms the state-of-the-art defenses against various model extraction attacks with a relatively low cost to the model accuracy. The artifact is publicly available at https://anonymous.4open.science/r/queen implementation-5408/.

Large Language Models for Link Stealing Attacks Against Graph Neural Networks

Graph data contains rich node features and unique edge information, which have been applied across various domains, such as citation networks or recommendation systems. Graph Neural Networks (GNNs) are specialized for handling such data and have shown impressive performance in many applications. However, GNNs may contain of sensitive information and susceptible to privacy attacks. For example, link stealing is a type of attack in which attackers infer whether two nodes are linked or not. Previous link stealing attacks primarily relied on posterior probabilities from the target GNN model, neglecting the significance of node features. Additionally, variations in node classes across different datasets lead to different dimensions of posterior probabilities. The handling of these varying data dimensions posed a challenge in using a single model to effectively conduct link stealing attacks on different datasets. To address these challenges, we introduce Large Language Models (LLMs) to perform link stealing attacks on GNNs. LLMs can effectively integrate textual features and exhibit strong generalizability, enabling attacks to handle diverse data dimensions across various datasets. We design two distinct LLM prompts to effectively combine textual features and posterior probabilities of graph nodes. Through these designed prompts, we fine-tune the LLM to adapt to the link stealing attack task. Furthermore, we fine-tune the LLM using multiple datasets and enable the LLM to learn features from different datasets simultaneously. Experimental results show that our approach significantly enhances the performance of existing link stealing attack tasks in both white-box and black-box scenarios. Our method can execute link stealing attacks across different datasets using only a single model, making link stealing attacks more applicable to real-world scenarios.

Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation

Federated learning is a promising privacy-preserving paradigm for distributed machine learning. In this context, there is sometimes a need for a specialized process called machine unlearning, which is required when the effect of some specific training samples needs to be removed from a learning model due to privacy, security, usability, and/or legislative factors. However, problems arise when current centralized unlearning methods are applied to existing federated learning, in which the server aims to remove all information about a class from the global model. Centralized unlearning usually focuses on simple models or is premised on the ability to access all training data at a central node. However, training data cannot be accessed on the server under the federated learning paradigm, conflicting with the requirements of the centralized unlearning process. Additionally, there are high computation and communication costs associated with accessing clients' data, especially in scenarios involving numerous clients or complex global models. To address these concerns, we propose a more effective and efficient federated unlearning scheme based on the concept of model explanation. Model explanation involves understanding deep networks and individual channel importance, so that this understanding can be used to determine which model channels are critical for classes that need to be unlearned. We select the most influential channels within an already-trained model for the data that need to be unlearned and fine-tune only influential channels to remove the contribution made by those data. In this way, we can simultaneously avoid huge consumption costs and ensure that the unlearned model maintains good performance. Experiments with different training models on various datasets demonstrate the effectiveness of the proposed approach.

Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions

Federated Learning (FL) is a distributed and privacy-preserving machine learning paradigm that coordinates multiple clients to train a model while keeping the raw data localized. However, this traditional FL poses some challenges, including privacy risks, data heterogeneity, communication bottlenecks, and system heterogeneity issues. To tackle these challenges, knowledge distillation (KD) has been widely applied in FL since 2020. KD is a validated and efficacious model compression and enhancement algorithm. The core concept of KD involves facilitating knowledge transfer between models by exchanging logits at intermediate or output layers. These properties make KD an excellent solution for the long-lasting challenges in FL. Up to now, there have been few reviews that summarize and analyze the current trend and methods for how KD can be applied in FL efficiently. This article aims to provide a comprehensive survey of KD-based FL, focusing on addressing the above challenges. First, we provide an overview of KD-based FL, including its motivation, basics, taxonomy, and a comparison with traditional FL and where KD should execute. We also analyze the critical factors in KD-based FL in the appendix, including teachers, knowledge, data, and methods. We discuss how KD can address the challenges in FL, including privacy protection, data heterogeneity, communication efficiency, and personalization. Finally, we discuss the challenges facing KD-based FL algorithms and future research directions. We hope this survey can provide insights and guidance for researchers and practitioners in the FL area.