Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects

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.

Vertical Federated Learning: Taxonomies, Threats, and Prospects

Federated learning (FL) is the most popular distributed machine learning technique. FL allows machine-learning models to be trained without acquiring raw data to a single point for processing. Instead, local models are trained with local data; the models are then shared and combined. This approach preserves data privacy as locally trained models are shared instead of the raw data themselves. Broadly, FL can be divided into horizontal federated learning (HFL) and vertical federated learning (VFL). For the former, different parties hold different samples over the same set of features; for the latter, different parties hold different feature data belonging to the same set of samples. In a number of practical scenarios, VFL is more relevant than HFL as different companies (e.g., bank and retailer) hold different features (e.g., credit history and shopping history) for the same set of customers. Although VFL is an emerging area of research, it is not well-established compared to HFL. Besides, VFL-related studies are dispersed, and their connections are not intuitive. Thus, this survey aims to bring these VFL-related studies to one place. Firstly, we classify existing VFL structures and algorithms. Secondly, we present the threats from security and privacy perspectives to VFL. Thirdly, for the benefit of future researchers, we discussed the challenges and prospects of VFL in detail.

MACAB: Model-Agnostic Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World

Object detection is the foundation of various critical computer-vision tasks such as segmentation, object tracking, and event detection. To train an object detector with satisfactory accuracy, a large amount of data is required. However, due to the intensive workforce involved with annotating large datasets, such a data curation task is often outsourced to a third party or relied on volunteers. This work reveals severe vulnerabilities of such data curation pipeline. We propose MACAB that crafts clean-annotated images to stealthily implant the backdoor into the object detectors trained on them even when the data curator can manually audit the images. We observe that the backdoor effect of both misclassification and the cloaking are robustly achieved in the wild when the backdoor is activated with inconspicuously natural physical triggers. Backdooring non-classification object detection with clean-annotation is challenging compared to backdooring existing image classification tasks with clean-label, owing to the complexity of having multiple objects within each frame, including victim and non-victim objects. The efficacy of the MACAB is ensured by constructively i abusing the image-scaling function used by the deep learning framework, ii incorporating the proposed adversarial clean image replica technique, and iii combining poison data selection criteria given constrained attacking budget. Extensive experiments demonstrate that MACAB exhibits more than 90% attack success rate under various real-world scenes. This includes both cloaking and misclassification backdoor effect even restricted with a small attack budget. The poisoned samples cannot be effectively identified by state-of-the-art detection techniques.The comprehensive video demo is at https://youtu.be/MA7L_LpXkp4, which is based on a poison rate of 0.14% for YOLOv4 cloaking backdoor and Faster R-CNN misclassification backdoor.

CASSOCK: Viable Backdoor Attacks against DNN in The Wall of Source-Specific Backdoor Defences

Backdoor attacks have been a critical threat to deep neural network (DNN). However, most existing countermeasures focus on source-agnostic backdoor attacks (SABAs) and fail to defeat source-specific backdoor attacks (SSBAs). Compared to an SABA, an SSBA activates a backdoor when an input from attacker-chosen class(es) is stamped with an attacker-specified trigger, making itself stealthier and thus evade most existing backdoor mitigation. Nonetheless, existing SSBAs have trade-offs on attack success rate (ASR, a backdoor is activated by a trigger input from a source class as expected) and false positive rate (FPR, a backdoor is activated unexpectedly by a trigger input from a non-source class). Significantly, they can still be effectively detected by the state-of-the-art (SOTA) countermeasures targeting SSBAs. This work overcomes efficiency and effectiveness deficiencies of existing SSBAs, thus bypassing the SOTA defences. The key insight is to construct desired poisoned and cover data during backdoor training by characterising SSBAs in-depth. Both data are samples with triggers: the cover/poisoned data from non-source/source class(es) holds ground-truth/target labels. Therefore, two cover/poisoned data enhancements are developed from trigger style and content, respectively, coined CASSOCK. First, we leverage trigger patterns with discrepant transparency to craft cover/poisoned data, enforcing triggers with heterogeneous sensitivity on different classes. The second enhancement chooses the target class features as triggers to craft these samples, entangling trigger features with the target class heavily. Compared with existing SSBAs, CASSOCK-based attacks have higher ASR and low FPR on four popular tasks: MNIST, CIFAR10, GTSRB, and LFW. More importantly, CASSOCK has effectively evaded three defences (SCAn, Februus and extended Neural Cleanse) already defeat existing SSBAs effectively.

Towards A Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasures

Since Deep Learning (DL) backdoor attacks have been revealed as one of the most insidious adversarial attacks, a number of countermeasures have been developed with certain assumptions defined in their respective threat models. However, the robustness of these countermeasures is inadvertently ignored, which can introduce severe consequences, e.g., a countermeasure can be misused and result in a false implication of backdoor detection. For the first time, we critically examine the robustness of existing backdoor countermeasures with an initial focus on three influential model-inspection ones that are Neural Cleanse (S&P'19), ABS (CCS'19), and MNTD (S&P'21). Although the three countermeasures claim that they work well under their respective threat models, they have inherent unexplored non-robust cases depending on factors such as given tasks, model architectures, datasets, and defense hyper-parameter, which are \textit{not even rooted from delicate adaptive attacks}. We demonstrate how to trivially bypass them aligned with their respective threat models by simply varying aforementioned factors. Particularly, for each defense, formal proofs or empirical studies are used to reveal its two non-robust cases where it is not as robust as it claims or expects, especially the recent MNTD. This work highlights the necessity of thoroughly evaluating the robustness of backdoor countermeasures to avoid their misleading security implications in unknown non-robust cases.

Sufficient Reasons for A Zero-Day Intrusion Detection Artificial Immune System

The Internet is the most complex machine humankind has ever built, and how to defense it from intrusions is even more complex. With the ever increasing of new intrusions, intrusion detection task rely on Artificial Intelligence more and more. Interpretability and transparency of the machine learning model is the foundation of trust in AI-driven intrusion detection results. Current interpretation Artificial Intelligence technologies in intrusion detection are heuristic, which is neither accurate nor sufficient. This paper proposed a rigorous interpretable Artificial Intelligence driven intrusion detection approach, based on artificial immune system. Details of rigorous interpretation calculation process for a decision tree model is presented. Prime implicant explanation for benign traffic flow are given in detail as rule for negative selection of the cyber immune system. Experiments are carried out in real-life traffic.

PPA: Preference Profiling Attack Against Federated Learning

Federated learning (FL) trains a global model across a number of decentralized participants, each with a local dataset. Compared to traditional centralized learning, FL does not require direct local datasets access and thus mitigates data security and privacy concerns. However, data privacy concerns for FL still exist due to inference attacks, including known membership inference, property inference, and data inversion. In this work, we reveal a new type of privacy inference attack, coined Preference Profiling Attack (PPA), that accurately profiles private preferences of a local user. In general, the PPA can profile top-k, especially for top-1, preferences contingent on the local 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, the 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 the PPA. We have extensively evaluated the PPA's effectiveness using four datasets from the image domains of MNIST, CIFAR10, Products-10K and RAF-DB. Our results show that the PPA achieves 90% and 98% top-1 attack accuracy to the MNIST and CIFAR10, respectively. More importantly, in the real-world commercial scenarios of shopping (i.e., Products-10K) and the social network (i.e., RAF-DB), the PPA gains a top-1 attack accuracy of 78% in the former case to infer the most ordered items, and 88% in the latter case to infer a victim user's emotions. Although existing countermeasures such as dropout and differential privacy protection can lower the PPA's accuracy to some extent, they unavoidably incur notable global model deterioration.

Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World

Deep learning models have been shown to be vulnerable to recent backdoor attacks. A backdoored model behaves normally for inputs containing no attacker-secretly-chosen trigger and maliciously for inputs with the trigger. To date, backdoor attacks and countermeasures mainly focus on image classification tasks. And most of them are implemented in the digital world with digital triggers. Besides the classification tasks, object detection systems are also considered as one of the basic foundations of computer vision tasks. However, there is no investigation and understanding of the backdoor vulnerability of the object detector, even in the digital world with digital triggers. For the first time, this work demonstrates that existing object detectors are inherently susceptible to physical backdoor attacks. We use a natural T-shirt bought from a market as a trigger to enable the cloaking effect--the person bounding-box disappears in front of the object detector. We show that such a backdoor can be implanted from two exploitable attack scenarios into the object detector, which is outsourced or fine-tuned through a pretrained model. We have extensively evaluated three popular object detection algorithms: anchor-based Yolo-V3, Yolo-V4, and anchor-free CenterNet. Building upon 19 videos shot in real-world scenes, we confirm that the backdoor attack is robust against various factors: movement, distance, angle, non-rigid deformation, and lighting. Specifically, the attack success rate (ASR) in most videos is 100% or close to it, while the clean data accuracy of the backdoored model is the same as its clean counterpart. The latter implies that it is infeasible to detect the backdoor behavior merely through a validation set. The averaged ASR still remains sufficiently high to be 78% in the transfer learning attack scenarios evaluated on CenterNet. See the demo video on https://youtu.be/Q3HOF4OobbY.

NTD: Non-Transferability Enabled Backdoor Detection

A backdoor deep learning (DL) model behaves normally upon clean inputs but misbehaves upon trigger inputs as the backdoor attacker desires, posing severe consequences to DL model deployments. State-of-the-art defenses are either limited to specific backdoor attacks (source-agnostic attacks) or non-user-friendly in that machine learning (ML) expertise or expensive computing resources are required. This work observes that all existing backdoor attacks have an inevitable intrinsic weakness, non-transferability, that is, a trigger input hijacks a backdoored model but cannot be effective to another model that has not been implanted with the same backdoor. With this key observation, we propose non-transferability enabled backdoor detection (NTD) to identify trigger inputs for a model-under-test (MUT) during run-time.Specifically, NTD allows a potentially backdoored MUT to predict a class for an input. In the meantime, NTD leverages a feature extractor (FE) to extract feature vectors for the input and a group of samples randomly picked from its predicted class, and then compares similarity between the input and the samples in the FE's latent space. If the similarity is low, the input is an adversarial trigger input; otherwise, benign. The FE is a free pre-trained model privately reserved from open platforms. As the FE and MUT are from different sources, the attacker is very unlikely to insert the same backdoor into both of them. Because of non-transferability, a trigger effect that does work on the MUT cannot be transferred to the FE, making NTD effective against different types of backdoor attacks. We evaluate NTD on three popular customized tasks such as face recognition, traffic sign recognition and general animal classification, results of which affirm that NDT has high effectiveness (low false acceptance rate) and usability (low false rejection rate) with low detection latency.

Quantization Backdoors to Deep Learning Models

There is currently a burgeoning demand for deploying deep learning (DL) models on ubiquitous edge Internet of Things devices attributing to their low latency and high privacy preservation. However, DL models are often large in size and require large-scale computation, which prevents them from being placed directly onto IoT devices where resources are constrained and 32-bit floating-point operations are unavailable. Model quantization is a pragmatic solution, which enables DL deployment on mobile devices and embedded systems by effortlessly post-quantizing a large high-precision model into a small low-precision model while retaining the model inference accuracy. This work reveals that the standard quantization operation can be abused to activate a backdoor. We demonstrate that a full-precision backdoored model that does not have any backdoor effect in the presence of a trigger -- as the backdoor is dormant -- can be activated by the default TensorFlow-Lite quantization, the only product-ready quantization framework to date. We ascertain that all trained float-32 backdoored models exhibit no backdoor effect even in the presence of trigger inputs. State-of-the-art frontend detection approaches, such as Neural Cleanse and STRIP, fail to identify the backdoor in the float-32 models. When each of the float-32 models is converted into an int-8 format model through the standard TFLite post-training quantization, the backdoor is activated in the quantized model, which shows a stable attack success rate close to 100% upon inputs with the trigger, while behaves normally upon non-trigger inputs. This work highlights that a stealthy security threat occurs when end users utilize the on-device post-training model quantization toolkits, informing security researchers of cross-platform overhaul of DL models post quantization even if they pass frontend inspections.