Search

In the burgeoning domain of machine learning, the reliance on third-party services for model training and the adoption of pre-trained models have surged. However, this reliance introduces vulnerabilities to model hijacking attacks, where adversaries manipulate models to perform unintended tasks, leading to significant security and ethical concerns, like turning an ordinary image classifier into a tool for detecting faces in pornographic content, all without the model owner's knowledge. This paper introduces Category-Agnostic Model Hijacking (CAMH), a novel model hijacking attack method capable of addressing the challenges of class number mismatch, data distribution divergence, and performance balance between the original and hijacking tasks. CAMH incorporates synchronized training layers, random noise optimization, and a dual-loop optimization approach to ensure minimal impact on the original task's performance while effectively executing the hijacking task. We evaluate CAMH across multiple benchmark datasets and network architectures, demonstrating its potent attack effectiveness while ensuring minimal degradation in the performance of the original task., Comment: 9 pages

Deep neural networks (DNNs) are vulnerable to adversarial examples (AEs) that mislead the model while appearing benign to human observers. A critical concern is the transferability of AEs, which enables black-box attacks without direct access to the target model. However, many previous attacks have failed to explain the intrinsic mechanism of adversarial transferability. In this paper, we rethink the property of transferable AEs and reformalize the formulation of transferability. Building on insights from this mechanism, we analyze the generalization of AEs across models with different architectures and prove that we can find a local perturbation to mitigate the gap between surrogate and target models. We further establish the inner connections between model smoothness and flat local maxima, both of which contribute to the transferability of AEs. Further, we propose a new adversarial attack algorithm, \textbf{A}dversarial \textbf{W}eight \textbf{T}uning (AWT), which adaptively adjusts the parameters of the surrogate model using generated AEs to optimize the flat local maxima and model smoothness simultaneously, without the need for extra data. AWT is a data-free tuning method that combines gradient-based and model-based attack methods to enhance the transferability of AEs. Extensive experiments on a variety of models with different architectures on ImageNet demonstrate that AWT yields superior performance over other attacks, with an average increase of nearly 5\% and 10\% attack success rates on CNN-based and Transformer-based models, respectively, compared to state-of-the-art attacks., Comment: 13 pages

The concept of the right to be forgotten has led to growing interest in machine unlearning, but reliable validation methods are lacking, creating opportunities for dishonest model providers to mislead data contributors. Traditional invasive methods like backdoor injection are not feasible for legacy data. To address this, we introduce TruVRF, a non-invasive unlearning verification framework operating at class-, volume-, and sample-level granularities. TruVRF includes three Unlearning-Metrics designed to detect different types of dishonest servers: Neglecting, Lazy, and Deceiving. Unlearning-Metric-I checks class alignment, Unlearning-Metric-II verifies sample count, and Unlearning-Metric-III confirms specific sample deletion. Evaluations on three datasets show TruVRF's robust performance, with over 90% accuracy for Metrics I and III, and a 4.8% to 8.2% inference deviation for Metric II. TruVRF also demonstrates generalizability and practicality across various conditions and with state-of-the-art unlearning frameworks like SISA and Amnesiac Unlearning.

In contrast to prevalent Federated Learning (FL) privacy inference techniques such as generative adversarial networks attacks, membership inference attacks, property inference attacks, and model inversion attacks, we devise an innovative privacy threat: the Data Distribution Decompose Attack on FL, termed Decaf. This attack enables an honest-but-curious FL server to meticulously profile the proportion of each class owned by the victim FL user, divulging sensitive information like local market item distribution and business competitiveness. The crux of Decaf lies in the profound observation that the magnitude of local model gradient changes closely mirrors the underlying data distribution, including the proportion of each class. Decaf addresses two crucial challenges: accurately identify the missing/null class(es) given by any victim user as a premise and then quantify the precise relationship between gradient changes and each remaining non-null class. Notably, Decaf operates stealthily, rendering it entirely passive and undetectable to victim users regarding the infringement of their data distribution privacy. Experimental validation on five benchmark datasets (MNIST, FASHION-MNIST, CIFAR-10, FER-2013, and SkinCancer) employing diverse model architectures, including customized convolutional networks, standardized VGG16, and ResNet18, demonstrates Decaf's efficacy. Results indicate its ability to accurately decompose local user data distribution, regardless of whether it is IID or non-IID distributed. Specifically, the dissimilarity measured using $L_{\infty}$ distance between the distribution decomposed by Decaf and ground truth is consistently below 5\% when no null classes exist. Moreover, Decaf achieves 100\% accuracy in determining any victim user's null classes, validated through formal proof.

Face Recognition Systems (FRS) have increasingly integrated into critical applications, including surveillance and user authentication, highlighting their pivotal role in modern security systems. Recent studies have revealed vulnerabilities in FRS to adversarial (e.g., adversarial patch attacks) and backdoor attacks (e.g., training data poisoning), raising significant concerns about their reliability and trustworthiness. Previous studies primarily focus on traditional adversarial or backdoor attacks, overlooking the resource-intensive or privileged-manipulation nature of such threats, thus limiting their practical generalization, stealthiness, universality and robustness. Correspondingly, in this paper, we delve into the inherent vulnerabilities in FRS through user studies and preliminary explorations. By exploiting these vulnerabilities, we identify a novel attack, facial identity backdoor attack dubbed FIBA, which unveils a potentially more devastating threat against FRS:an enrollment-stage backdoor attack. FIBA circumvents the limitations of traditional attacks, enabling broad-scale disruption by allowing any attacker donning a specific trigger to bypass these systems. This implies that after a single, poisoned example is inserted into the database, the corresponding trigger becomes a universal key for any attackers to spoof the FRS. This strategy essentially challenges the conventional attacks by initiating at the enrollment stage, dramatically transforming the threat landscape by poisoning the feature database rather than the training data., Comment: 19 pages,version 3

As a novel privacy-preserving paradigm aimed at reducing client computational costs and achieving data utility, split learning has garnered extensive attention and proliferated widespread applications across various fields, including smart health and smart transportation, among others. While recent studies have primarily concentrated on addressing privacy leakage concerns in split learning, such as inference attacks and data reconstruction, the exploration of security issues (e.g., backdoor attacks) within the framework of split learning has been comparatively limited. Nonetheless, the security vulnerability within the context of split learning is highly posing a threat and can give rise to grave security implications, such as the illegal impersonation in the face recognition model. Therefore, in this paper, we propose a stealthy backdoor attack strategy (namely SBAT) tailored to the without-label-sharing split learning architecture, which unveils the inherent security vulnerability of split learning. We posit the existence of a potential attacker on the server side aiming to introduce a backdoor into the training model, while exploring two scenarios: one with known client network architecture and the other with unknown architecture. Diverging from traditional backdoor attack methods that manipulate the training data and labels, we constructively conduct the backdoor attack by injecting the trigger embedding into the server network. Specifically, our SBAT achieves a higher level of attack stealthiness by refraining from modifying any intermediate parameters (e.g., gradients) during training and instead executing all malicious operations post-training., Comment: 15 pages

Backdoor attacks have attracted wide attention from academia and industry due to their great security threat to deep neural networks (DNN). Most of the existing methods propose to conduct backdoor attacks by poisoning the training dataset with different strategies, so it's critical to identify the poisoned samples and then train a clean model on the unreliable dataset in the context of defending backdoor attacks. Although numerous backdoor countermeasure researches are proposed, their inherent weaknesses render them limited in practical scenarios, such as the requirement of enough clean samples, unstable defense performance under various attack conditions, poor defense performance against adaptive attacks, and so on.Therefore, in this paper, we are committed to overcome the above limitations and propose a more practical backdoor defense method. Concretely, we first explore the inherent relationship between the potential perturbations and the backdoor trigger, and the theoretical analysis and experimental results demonstrate that the poisoned samples perform more robustness to perturbation than the clean ones. Then, based on our key explorations, we introduce AdvrBD, an Adversarial perturbation-based and robust Backdoor Defense framework, which can effectively identify the poisoned samples and train a clean model on the poisoned dataset. Constructively, our AdvrBD eliminates the requirement for any clean samples or knowledge about the poisoned dataset (e.g., poisoning ratio), which significantly improves the practicality in real-world scenarios., Comment: 13 pages, under review

Personal digital data is a critical asset, and governments worldwide have enforced laws and regulations to protect data privacy. Data users have been endowed with the right to be forgotten of their data. In the course of machine learning (ML), the forgotten right requires a model provider to delete user data and its subsequent impact on ML models upon user requests. Machine unlearning emerges to address this, which has garnered ever-increasing attention from both industry and academia. While the area has developed rapidly, there is a lack of comprehensive surveys to capture the latest advancements. Recognizing this shortage, we conduct an extensive exploration to map the landscape of machine unlearning including the (fine-grained) taxonomy of unlearning algorithms under centralized and distributed settings, debate on approximate unlearning, verification and evaluation metrics, challenges and solutions for unlearning under different applications, as well as attacks targeting machine unlearning. The survey concludes by outlining potential directions for future research, hoping to serve as a guide for interested scholars.

Federated learning (FL) trains a global model across a number of decentralized users, each with a local dataset. Compared to traditional centralized learning, FL does not require direct access to local datasets and thus aims to mitigate data privacy concerns. However, data privacy leakage in FL still exists due to inference attacks, including membership inference, property inference, and data inversion. In this work, we propose a new type of privacy inference attack, coined Preference Profiling Attack (PPA), that accurately profiles the private preferences of a local user, e.g., most liked (disliked) items from the client's online shopping and most common expressions from the user's selfies. In general, PPA can profile top-k (i.e., k = 1, 2, 3 and k = 1 in particular) preferences contingent on the local client (user)'s characteristics. Our key insight is that the gradient variation of a local user's model has a distinguishable sensitivity to the sample proportion of a given class, especially the majority (minority) class. By observing a user model's gradient sensitivity to a class, PPA can profile the sample proportion of the class in the user's local dataset, and thus the user's preference of the class is exposed. The inherent statistical heterogeneity of FL further facilitates PPA. We have extensively evaluated the PPA's effectiveness using four datasets (MNIST, CIFAR10, RAF-DB and Products-10K). Our results show that PPA achieves 90% and 98% top-1 attack accuracy to the MNIST and CIFAR10, respectively. More importantly, in real-world commercial scenarios of shopping (i.e., Products-10K) and social network (i.e., RAF-DB), PPA gains a top-1 attack accuracy of 78% in the former case to infer the most ordered items (i.e., as a commercial competitor), and 88% in the latter case to infer a victim user's most often facial expressions, e.g., disgusted.