Fake or Compromised? Making Sense of Malicious Clients in Federated Learning

Federated learning (FL) is a distributed machine learning paradigm that enables training models on decentralized data. The field of FL security against poisoning attacks is plagued with confusion due to the proliferation of research that makes different assumptions about the capabilities of adversaries and the adversary models they operate under. Our work aims to clarify this confusion by presenting a comprehensive analysis of the various poisoning attacks and defensive aggregation rules (AGRs) proposed in the literature, and connecting them under a common framework. To connect existing adversary models, we present a hybrid adversary model, which lies in the middle of the spectrum of adversaries, where the adversary compromises a few clients, trains a generative (e.g., DDPM) model with their compromised samples, and generates new synthetic data to solve an optimization for a stronger (e.g., cheaper, more practical) attack against different robust aggregation rules. By presenting the spectrum of FL adversaries, we aim to provide practitioners and researchers with a clear understanding of the different types of threats they need to consider when designing FL systems, and identify areas where further research is needed.

SoK: Challenges and Opportunities in Federated Unlearning

Federated learning (FL), introduced in 2017, facilitates collaborative learning between non-trusting parties with no need for the parties to explicitly share their data among themselves. This allows training models on user data while respecting privacy regulations such as GDPR and CPRA. However, emerging privacy requirements may mandate model owners to be able to \emph{forget} some learned data, e.g., when requested by data owners or law enforcement. This has given birth to an active field of research called \emph{machine unlearning}. In the context of FL, many techniques developed for unlearning in centralized settings are not trivially applicable! This is due to the unique differences between centralized and distributed learning, in particular, interactivity, stochasticity, heterogeneity, and limited accessibility in FL. In response, a recent line of work has focused on developing unlearning mechanisms tailored to FL. This SoK paper aims to take a deep look at the \emph{federated unlearning} literature, with the goal of identifying research trends and challenges in this emerging field. By carefully categorizing papers published on FL unlearning (since 2020), we aim to pinpoint the unique complexities of federated unlearning, highlighting limitations on directly applying centralized unlearning methods. We compare existing federated unlearning methods regarding influence removal and performance recovery, compare their threat models and assumptions, and discuss their implications and limitations. For instance, we analyze the experimental setup of FL unlearning studies from various perspectives, including data heterogeneity and its simulation, the datasets used for demonstration, and evaluation metrics. Our work aims to offer insights and suggestions for future research on federated unlearning.

Diffence: Fencing Membership Privacy With Diffusion Models

Deep learning models, while achieving remarkable performance across various tasks, are vulnerable to member inference attacks, wherein adversaries identify if a specific data point was part of a model's training set. This susceptibility raises substantial privacy concerns, especially when models are trained on sensitive datasets. Current defense methods often struggle to provide robust protection without hurting model utility, and they often require retraining the model or using extra data. In this work, we introduce a novel defense framework against membership attacks by leveraging generative models. The key intuition of our defense is to remove the differences between member and non-member inputs which can be used to perform membership attacks, by re-generating input samples before feeding them to the target model. Therefore, our defense works \emph{pre-inference}, which is unlike prior defenses that are either training-time (modify the model) or post-inference time (modify the model's output). A unique feature of our defense is that it works on input samples only, without modifying the training or inference phase of the target model. Therefore, it can be cascaded with other defense mechanisms as we demonstrate through experiments. Through extensive experimentation, we show that our approach can serve as a robust plug-n-play defense mechanism, enhancing membership privacy without compromising model utility in both baseline and defended settings. For example, our method enhanced the effectiveness of recent state-of-the-art defenses, reducing attack accuracy by an average of 5.7\% to 12.4\% across three datasets, without any impact on the model's accuracy. By integrating our method with prior defenses, we achieve new state-of-the-art performance in the privacy-utility trade-off.

Understanding (Un)Intended Memorization in Text-to-Image Generative Models

Multimodal machine learning, especially text-to-image models like Stable Diffusion and DALL-E 3, has gained significance for transforming text into detailed images. Despite their growing use and remarkable generative capabilities, there is a pressing need for a detailed examination of these models' behavior, particularly with respect to memorization. Historically, memorization in machine learning has been context-dependent, with diverse definitions emerging from classification tasks to complex models like Large Language Models (LLMs) and Diffusion models. Yet, a definitive concept of memorization that aligns with the intricacies of text-to-image synthesis remains elusive. This understanding is vital as memorization poses privacy risks yet is essential for meeting user expectations, especially when generating representations of underrepresented entities. In this paper, we introduce a specialized definition of memorization tailored to text-to-image models, categorizing it into three distinct types according to user expectations. We closely examine the subtle distinctions between intended and unintended memorization, emphasizing the importance of balancing user privacy with the generative quality of the model outputs. Using the Stable Diffusion model, we offer examples to validate our memorization definitions and clarify their application.

Memory Triggers: Unveiling Memorization in Text-To-Image Generative Models through Word-Level Duplication

Diffusion-based models, such as the Stable Diffusion model, have revolutionized text-to-image synthesis with their ability to produce high-quality, high-resolution images. These advancements have prompted significant progress in image generation and editing tasks. However, these models also raise concerns due to their tendency to memorize and potentially replicate exact training samples, posing privacy risks and enabling adversarial attacks. Duplication in training datasets is recognized as a major factor contributing to memorization, and various forms of memorization have been studied so far. This paper focuses on two distinct and underexplored types of duplication that lead to replication during inference in diffusion-based models, particularly in the Stable Diffusion model. We delve into these lesser-studied duplication phenomena and their implications through two case studies, aiming to contribute to the safer and more responsible use of generative models in various applications.

RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Active Data Manipulation

Federated learning (FL) has recently emerged as a privacy-preserving approach for machine learning in domains that rely on user interactions, particularly recommender systems (RS) and online learning to rank (OLTR). While there has been substantial research on the privacy of traditional FL, little attention has been paid to studying the privacy properties of these interaction-based FL (IFL) systems. In this work, we show that IFL can introduce unique challenges concerning user privacy, particularly when the central server has knowledge and control over the items that users interact with. Specifically, we demonstrate the threat of reconstructing user interactions by presenting RAIFLE, a general optimization-based reconstruction attack framework customized for IFL. RAIFLE employs Active Data Manipulation (ADM), a novel attack technique unique to IFL, where the server actively manipulates the training features of the items to induce adversarial behaviors in the local FL updates. We show that RAIFLE is more impactful than existing FL privacy attacks in the IFL context, and describe how it can undermine privacy defenses like secure aggregation and private information retrieval. Based on our findings, we propose and discuss countermeasure guidelines to mitigate our attack in the context of federated RS/OLTR specifically and IFL more broadly.

Realistic Website Fingerprinting By Augmenting Network Trace

Website Fingerprinting (WF) is considered a major threat to the anonymity of Tor users (and other anonymity systems). While state-of-the-art WF techniques have claimed high attack accuracies, e.g., by leveraging Deep Neural Networks (DNN), several recent works have questioned the practicality of such WF attacks in the real world due to the assumptions made in the design and evaluation of these attacks. In this work, we argue that such impracticality issues are mainly due to the attacker's inability in collecting training data in comprehensive network conditions, e.g., a WF classifier may be trained only on samples collected on specific high-bandwidth network links but deployed on connections with different network conditions. We show that augmenting network traces can enhance the performance of WF classifiers in unobserved network conditions. Specifically, we introduce NetAugment, an augmentation technique tailored to the specifications of Tor traces. We instantiate NetAugment through semi-supervised and self-supervised learning techniques. Our extensive open-world and close-world experiments demonstrate that under practical evaluation settings, our WF attacks provide superior performances compared to the state-of-the-art; this is due to their use of augmented network traces for training, which allows them to learn the features of target traffic in unobserved settings. For instance, with a 5-shot learning in a closed-world scenario, our self-supervised WF attack (named NetCLR) reaches up to 80% accuracy when the traces for evaluation are collected in a setting unobserved by the WF adversary. This is compared to an accuracy of 64.4% achieved by the state-of-the-art Triplet Fingerprinting [35]. We believe that the promising results of our work can encourage the use of network trace augmentation in other types of network traffic analysis.

On the Risks of Stealing the Decoding Algorithms of Language Models

A key component of generating text from modern language models (LM) is the selection and tuning of decoding algorithms. These algorithms determine how to generate text from the internal probability distribution generated by the LM. The process of choosing a decoding algorithm and tuning its hyperparameters takes significant time, manual effort, and computation, and it also requires extensive human evaluation. Therefore, the identity and hyperparameters of such decoding algorithms are considered to be extremely valuable to their owners. In this work, we show, for the first time, that an adversary with typical API access to an LM can steal the type and hyperparameters of its decoding algorithms at very low monetary costs. Our attack is effective against popular LMs used in text generation APIs, including GPT-2 and GPT-3. We demonstrate the feasibility of stealing such information with only a few dollars, e.g., $\$0.8$, $\$1$, $\$4$, and $\$40$ for the four versions of GPT-3.

Security Analysis of SplitFed Learning

Split Learning (SL) and Federated Learning (FL) are two prominent distributed collaborative learning techniques that maintain data privacy by allowing clients to never share their private data with other clients and servers, and fined extensive IoT applications in smart healthcare, smart cities, and smart industry. Prior work has extensively explored the security vulnerabilities of FL in the form of poisoning attacks. To mitigate the effect of these attacks, several defenses have also been proposed. Recently, a hybrid of both learning techniques has emerged (commonly known as SplitFed) that capitalizes on their advantages (fast training) and eliminates their intrinsic disadvantages (centralized model updates). In this paper, we perform the first ever empirical analysis of SplitFed's robustness to strong model poisoning attacks. We observe that the model updates in SplitFed have significantly smaller dimensionality as compared to FL that is known to have the curse of dimensionality. We show that large models that have higher dimensionality are more susceptible to privacy and security attacks, whereas the clients in SplitFed do not have the complete model and have lower dimensionality, making them more robust to existing model poisoning attacks. Our results show that the accuracy reduction due to the model poisoning attack is 5x lower for SplitFed compared to FL.

E2FL: Equal and Equitable Federated Learning

Federated Learning (FL) enables data owners to train a shared global model without sharing their private data. Unfortunately, FL is susceptible to an intrinsic fairness issue: due to heterogeneity in clients' data distributions, the final trained model can give disproportionate advantages across the participating clients. In this work, we present Equal and Equitable Federated Learning (E2FL) to produce fair federated learning models by preserving two main fairness properties, equity and equality, concurrently. We validate the efficiency and fairness of E2FL in different real-world FL applications, and show that E2FL outperforms existing baselines in terms of the resulting efficiency, fairness of different groups, and fairness among all individual clients.