Search

The objective of digital forgetting is, given a model with undesirable knowledge or behavior, obtain a new model where the detected issues are no longer present. The motivations for forgetting include privacy protection, copyright protection, elimination of biases and discrimination, and prevention of harmful content generation. Effective digital forgetting has to be effective (meaning how well the new model has forgotten the undesired knowledge/behavior), retain the performance of the original model on the desirable tasks, and be scalable (in particular forgetting has to be more efficient than retraining from scratch on just the tasks/data to be retained). This survey focuses on forgetting in large language models (LLMs). We first provide background on LLMs, including their components, the types of LLMs, and their usual training pipeline. Second, we describe the motivations, types, and desired properties of digital forgetting. Third, we introduce the approaches to digital forgetting in LLMs, among which unlearning methodologies stand out as the state of the art. Fourth, we provide a detailed taxonomy of machine unlearning methods for LLMs, and we survey and compare current approaches. Fifth, we detail datasets, models and metrics used for the evaluation of forgetting, retaining and runtime. Sixth, we discuss challenges in the area. Finally, we provide some concluding remarks., Comment: 70 pages

$\epsilon$-Differential privacy (DP) is a well-known privacy model that offers strong privacy guarantees. However, when applied to data releases, DP significantly deteriorates the analytical utility of the protected outcomes. To keep data utility at reasonable levels, practical applications of DP to data releases have used weak privacy parameters (large $\epsilon$), which dilute the privacy guarantees of DP. In this work, we tackle this issue by using an alternative formulation of the DP privacy guarantees, named $\epsilon$-individual differential privacy (iDP), which causes less data distortion while providing the same protection as DP to subjects. We enforce iDP in data releases by relying on attribute masking plus a pre-processing step based on data microaggregation. The goal of this step is to reduce the sensitivity to record changes, which determines the amount of noise required to enforce iDP (and DP). Specifically, we propose data microaggregation strategies designed for iDP whose sensitivities are significantly lower than those used in DP. As a result, we obtain iDP-protected data with significantly better utility than with DP. We report on experiments that show how our approach can provide strong privacy (small $\epsilon$) while yielding protected data that do not significantly degrade the accuracy of secondary data analysis., Comment: 17 pages, 6 figures

Human facial data hold tremendous potential to address a variety of classification problems, including face recognition, age estimation, gender identification, emotion analysis, and race classification. However, recent privacy regulations, such as the EU General Data Protection Regulation and others, have restricted the ways in which human images may be collected and used for research. As a result, several previously published data sets containing human faces have been removed from the internet due to inadequate data collection methods that failed to meet privacy regulations. Data sets consisting of synthetic data have been proposed as an alternative, but they fall short of accurately representing the real data distribution. On the other hand, most available data sets are labeled for just a single task, which limits their applicability. To address these issues, we present the Multi-Task Faces (MTF) image data set, a meticulously curated collection of face images designed for various classification tasks, including face recognition, as well as race, gender, and age classification. The MTF data set has been ethically gathered by leveraging publicly available images of celebrities and strictly adhering to copyright regulations. In this paper, we present this data set and provide detailed descriptions of the followed data collection and processing procedures. Furthermore, we evaluate the performance of five deep learning (DL) models on the MTF data set across the aforementioned classification tasks. Additionally, we compare the performance of DL models over the processed MTF data and over raw data crawled from the internet. The reported results constitute a baseline for further research employing these data. The MTF data set can be accessed through the following link (please cite the present paper if you use the data set): https://github.com/RamiHaf/MTF_data_set, Comment: 21 pages, 2 figures, 9 Tables

The threat of reconstruction attacks has led the U.S. Census Bureau (USCB) to replace in the Decennial Census 2020 the traditional statistical disclosure limitation based on rank swapping with one based on differential privacy (DP), leading to substantial accuracy loss of released statistics. Yet, it has been argued that, if many different reconstructions are compatible with the released statistics, most of them do not correspond to actual original data, which protects against respondent reidentification. Recently, a new attack has been proposed, which incorporates the confidence that a reconstructed record was in the original data. The alleged risk of disclosure entailed by such confidence-ranked reconstruction has renewed the interest of the USCB to use DP-based solutions. To forestall a potential accuracy loss in future releases, we show that the proposed reconstruction is neither effective as a reconstruction method nor conducive to disclosure as claimed by its authors. Specifically, we report empirical results showing the proposed ranking cannot guide reidentification or attribute disclosure attacks, and hence fails to warrant the utility sacrifice entailed by the use of DP to release census statistical data., Comment: In Lecture Notes in Artificial Intelligence, vol. 14915, pp. 213-224. Vol. Privacy in Statistical Databases (PSD 2024), Antibes Juan-les-Pins, France, Sep. 25-27, 2024. 20 pages, 5 figures, 4 tables

Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models. Unfortunately, doing so facilitates a new training-time attack (i.e., backdoor attack) against DNNs. This attack aims to induce misclassification of input samples containing adversary-specified trigger patterns. In this paper, we first conduct a layer-wise feature analysis of poisoned and benign samples from the target class. We find out that the feature difference between benign and poisoned samples tends to be maximum at a critical layer, which is not always the one typically used in existing defenses, namely the layer before fully-connected layers. We also demonstrate how to locate this critical layer based on the behaviors of benign samples. We then propose a simple yet effective method to filter poisoned samples by analyzing the feature differences between suspicious and benign samples at the critical layer. We conduct extensive experiments on two benchmark datasets, which confirm the effectiveness of our defense., Comment: This paper is accepted by PAKDD 2023

In recent years, it has been claimed that releasing accurate statistical information on a database is likely to allow its complete reconstruction. Differential privacy has been suggested as the appropriate methodology to prevent these attacks. These claims have recently been taken very seriously by the U.S. Census Bureau and led them to adopt differential privacy for releasing U.S. Census data. This in turn has caused consternation among users of the Census data due to the lack of accuracy of the protected outputs. It has also brought legal action against the U.S. Department of Commerce. In this paper, we trace the origins of the claim that releasing information on a database automatically makes it vulnerable to being exposed by reconstruction attacks and we show that this claim is, in fact, incorrect. We also show that reconstruction can be averted by properly using traditional statistical disclosure control (SDC) techniques. We further show that the geographic level at which exact counts are released is even more relevant to protection than the actual SDC method employed. Finally, we caution against confusing reconstruction and reidentification: using the quality of reconstruction as a metric of reidentification results in exaggerated reidentification risk figures., Comment: Journal of Official Statistics (to appear)

TREs are widely, and increasingly used to support statistical analysis of sensitive data across a range of sectors (e.g., health, police, tax and education) as they enable secure and transparent research whilst protecting data confidentiality. There is an increasing desire from academia and industry to train AI models in TREs. The field of AI is developing quickly with applications including spotting human errors, streamlining processes, task automation and decision support. These complex AI models require more information to describe and reproduce, increasing the possibility that sensitive personal data can be inferred from such descriptions. TREs do not have mature processes and controls against these risks. This is a complex topic, and it is unreasonable to expect all TREs to be aware of all risks or that TRE researchers have addressed these risks in AI-specific training. GRAIMATTER has developed a draft set of usable recommendations for TREs to guard against the additional risks when disclosing trained AI models from TREs. The development of these recommendations has been funded by the GRAIMATTER UKRI DARE UK sprint research project. This version of our recommendations was published at the end of the project in September 2022. During the course of the project, we have identified many areas for future investigations to expand and test these recommendations in practice. Therefore, we expect that this document will evolve over time.

In federated learning (FL), a set of participants share updates computed on their local data with an aggregator server that combines updates into a global model. However, reconciling accuracy with privacy and security is a challenge to FL. On the one hand, good updates sent by honest participants may reveal their private local information, whereas poisoned updates sent by malicious participants may compromise the model's availability and/or integrity. On the other hand, enhancing privacy via update distortion damages accuracy, whereas doing so via update aggregation damages security because it does not allow the server to filter out individual poisoned updates. To tackle the accuracy-privacy-security conflict, we propose {\em fragmented federated learning} (FFL), in which participants randomly exchange and mix fragments of their updates before sending them to the server. To achieve privacy, we design a lightweight protocol that allows participants to privately exchange and mix encrypted fragments of their updates so that the server can neither obtain individual updates nor link them to their originators. To achieve security, we design a reputation-based defense tailored for FFL that builds trust in participants and their mixed updates based on the quality of the fragments they exchange and the mixed updates they send. Since the exchanged fragments' parameters keep their original coordinates and attackers can be neutralized, the server can correctly reconstruct a global model from the received mixed updates without accuracy loss. Experiments on four real data sets show that FFL can prevent semi-honest servers from mounting privacy attacks, can effectively counter poisoning attacks and can keep the accuracy of the global model., Comment: IEEE Transactions on Neural Networks and Learning Systems (To Appear)

We introduce a new privacy model relying on bistochastic matrices, that is, matrices whose components are nonnegative and sum to 1 both row-wise and column-wise. This class of matrices is used to both define privacy guarantees and a tool to apply protection on a data set. The bistochasticity assumption happens to connect several fields of the privacy literature, including the two most popular models, k-anonymity and differential privacy. Moreover, it establishes a bridge with information theory, which simplifies the thorny issue of evaluating the utility of a protected data set. Bistochastic privacy also clarifies the trade-off between protection and utility by using bits, which can be viewed as a natural currency to comprehend and operationalize this trade-off, in the same way than bits are used in information theory to capture uncertainty. A discussion on the suitable parameterization of bistochastic matrices to achieve the privacy guarantees of this new model is also provided., Comment: To be published in Lecture Notes in Artificial Intelligence vol 13408, Modeling Decisions for Artificial Intelligence 19th International Conference MDAI 2022, Sant Cugat, Catalonia, August 30 - 2 September 2022

Federated learning (FL) provides autonomy and privacy by design to participating peers, who cooperatively build a machine learning (ML) model while keeping their private data in their devices. However, that same autonomy opens the door for malicious peers to poison the model by conducting either untargeted or targeted poisoning attacks. The label-flipping (LF) attack is a targeted poisoning attack where the attackers poison their training data by flipping the labels of some examples from one class (i.e., the source class) to another (i.e., the target class). Unfortunately, this attack is easy to perform and hard to detect and it negatively impacts on the performance of the global model. Existing defenses against LF are limited by assumptions on the distribution of the peers' data and/or do not perform well with high-dimensional models. In this paper, we deeply investigate the LF attack behavior and find that the contradicting objectives of attackers and honest peers on the source class examples are reflected in the parameter gradients corresponding to the neurons of the source and target classes in the output layer, making those gradients good discriminative features for the attack detection. Accordingly, we propose a novel defense that first dynamically extracts those gradients from the peers' local updates, and then clusters the extracted gradients, analyzes the resulting clusters and filters out potential bad updates before model aggregation. Extensive empirical analysis on three data sets shows the proposed defense's effectiveness against the LF attack regardless of the data distribution or model dimensionality. Also, the proposed defense outperforms several state-of-the-art defenses by offering lower test error, higher overall accuracy, higher source class accuracy, lower attack success rate, and higher stability of the source class accuracy.

Federated learning (FL) enables learning a global machine learning model from local data distributed among a set of participating workers. This makes it possible i) to train more accurate models due to learning from rich joint training data, and ii) to improve privacy by not sharing the workers' local private data with others. However, the distributed nature of FL makes it vulnerable to targeted poisoning attacks that negatively impact the integrity of the learned model while, unfortunately, being difficult to detect. Existing defenses against those attacks are limited by assumptions on the workers' data distribution, may degrade the global model performance on the main task and/or are ill-suited to high-dimensional models. In this paper, we analyze targeted attacks against FL and find that the neurons in the last layer of a deep learning (DL) model that are related to the attacks exhibit a different behavior from the unrelated neurons, making the last-layer gradients valuable features for attack detection. Accordingly, we propose \textit{FL-Defender} as a method to combat FL targeted attacks. It consists of i) engineering more robust discriminative features by calculating the worker-wise angle similarity for the workers' last-layer gradients, ii) compressing the resulting similarity vectors using PCA to reduce redundant information, and iii) re-weighting the workers' updates based on their deviation from the centroid of the compressed similarity vectors. Experiments on three data sets with different DL model sizes and data distributions show the effectiveness of our method at defending against label-flipping and backdoor attacks. Compared to several state-of-the-art defenses, FL-Defender achieves the lowest attack success rates, maintains the performance of the global model on the main task and causes minimal computational overhead on the server.

We review the use of differential privacy (DP) for privacy protection in machine learning (ML). We show that, driven by the aim of preserving the accuracy of the learned models, DP-based ML implementations are so loose that they do not offer the ex ante privacy guarantees of DP. Instead, what they deliver is basically noise addition similar to the traditional (and often criticized) statistical disclosure control approach. Due to the lack of formal privacy guarantees, the actual level of privacy offered must be experimentally assessed ex post, which is done very seldom. In this respect, we present empirical results showing that standard anti-overfitting techniques in ML can achieve a better utility/privacy/efficiency trade-off than DP., Comment: ACM Computing Surveys (to appear)

Multiparty computation (MPC) consists in several parties engaging in joint computation in such a way that each party's input and output remain private to that party. Whereas MPC protocols for specific computations have existed since the 1980s, only recently general-purpose compilers have been developed to allow MPC on arbitrary functions. Yet, using today's MPC compilers requires substantial programming effort and skill on the user's side, among other things because nearly all compilers translate the code of the computation into a Boolean or arithmetic circuit. In particular, the circuit representation requires unrolling loops and recursive calls, which forces programmers to (often manually) define loop bounds and hardly use recursion. We present an approach allowing MPC on an arbitrary computation expressed as ordinary code with all functionalities that does not need to be translated into a circuit. Our notion of input and output privacy is predicated on unlinkability. Our method leverages co-utile computation outsourcing using anonymous channels via decentralized reputation, makes a minimalistic use of cryptography and does not require participants to be honest-but-curious: it works as long as participants are rational (self-interested), which may include rationally malicious peers (who become attackers if this is advantageous to them). We present example applications, including e-voting. Our empirical work shows that reputation captures well the behavior of peers and ensures that parties with high reputation obtain correct results., Comment: IEEE Transactions on Dependable and Secure Computing, to appear