隐私攻击

Linear regression is a fundamental tool for statistical analysis. This has motivated the development of linear regression methods that also satisfy differential privacy and thus guarantee that the learned model reveals little about any one data point used to construct it. However, existing differentially private solutions assume that the end user can easily specify good data bounds and hyperparameters. Both present significant practical obstacles. In this paper, we study an algorithm which uses the exponential mechanism to select a model with high Tukey depth from a collection of non-private regression models. Given $n$ samples of $d$-dimensional data used to train $m$ models, we construct an efficient analogue using an approximate Tukey depth that runs in time $O(d^2n + dm\log(m))$. We find that this algorithm obtains strong empirical performance in the data-rich setting with no data bounds or hyperparameter selection required.

Privacy is a central tenet of Federated learning (FL), in which a central server trains models without centralizing user data. However, gradient updates used in FL can leak user information. While the most industrial uses of FL are for text applications (e.g. keystroke prediction), the majority of attacks on user privacy in FL have focused on simple image classifiers and threat models that assume honest execution of the FL protocol from the server. We propose a novel attack that reveals private user text by deploying malicious parameter vectors, and which succeeds even with mini-batches, multiple users, and long sequences. Unlike previous attacks on FL, the attack exploits characteristics of both the Transformer architecture and the token embedding, separately extracting tokens and positional embeddings to retrieve high-fidelity text. We argue that the threat model of malicious server states is highly relevant from a user-centric perspective, and show that in this scenario, text applications using transformer models are much more vulnerable than previously thought.

As machine learning becomes more widespread throughout society, aspects including data privacy and fairness must be carefully considered, and are crucial for deployment in highly regulated industries. Unfortunately, the application of privacy enhancing technologies can worsen unfair tendencies in models. In particular, one of the most widely used techniques for private model training, differentially private stochastic gradient descent (DPSGD), frequently intensifies disparate impact on groups within data. In this work we study the fine-grained causes of unfairness in DPSGD and identify gradient misalignment due to inequitable gradient clipping as the most significant source. This observation leads us to a new method for reducing unfairness by preventing gradient misalignment in DPSGD.

Differentially private deep learning has recently witnessed advances in computational efficiency and privacy-utility trade-off. We explore whether further improvements along the two axes are possible and provide affirmative answers leveraging two instantiations of \emph{group-wise clipping}. To reduce the compute time overhead of private learning, we show that \emph{per-layer clipping}, where the gradient of each neural network layer is clipped separately, allows clipping to be performed in conjunction with backpropagation in differentially private optimization. This results in private learning that is as memory-efficient and almost as fast per training update as non-private learning for many workflows of interest. While per-layer clipping with constant thresholds tends to underperform standard flat clipping, per-layer clipping with adaptive thresholds matches or outperforms flat clipping under given training epoch constraints, hence attaining similar or better task performance within less wall time. To explore the limits of scaling (pretrained) models in differentially private deep learning, we privately fine-tune the 175 billion-parameter GPT-3. We bypass scaling challenges associated with clipping gradients that are distributed across multiple devices with \emph{per-device clipping} that clips the gradient of each model piece separately on its host device. Privately fine-tuning GPT-3 with per-device clipping achieves a task performance at $\epsilon=1$ better than what is attainable by non-privately fine-tuning the largest GPT-2 on a summarization task.

Repeated parameter sharing in federated learning causes significant information leakage about private data, thus defeating its main purpose: data privacy. Mitigating the risk of this information leakage, using state of the art differentially private algorithms, also does not come for free. Randomized mechanisms can prevent convergence of models on learning even the useful representation functions, especially if there is more disagreement between local models on the classification functions (due to data heterogeneity). In this paper, we consider a representation federated learning objective that encourages various parties to collaboratively refine the consensus part of the model, with differential privacy guarantees, while separately allowing sufficient freedom for local personalization (without releasing it). We prove that in the linear representation setting, while the objective is non-convex, our proposed new algorithm \DPFEDREP\ converges to a ball centered around the \emph{global optimal} solution at a linear rate, and the radius of the ball is proportional to the reciprocal of the privacy budget. With this novel utility analysis, we improve the SOTA utility-privacy trade-off for this problem by a factor of $\sqrt{d}$, where $d$ is the input dimension. We empirically evaluate our method with the image classification task on CIFAR10, CIFAR100, and EMNIST, and observe a significant performance improvement over the prior work under the same small privacy budget. The code can be found in this link, https://github.com/shenzebang/CENTAUR-Privacy-Federated-Representation-Learning.

We propose a novel clustering mechanism based on an incompatibility property between subsets of data that emerges during model training. This mechanism partitions the dataset into subsets that generalize only to themselves, i.e., training on one subset does not improve performance on the other subsets. Leveraging the interaction between the dataset and the training process, our clustering mechanism partitions datasets into clusters that are defined by—and therefore meaningful to—the objective of the training process. We apply our clustering mechanism to defend against data poisoning attacks, in which the attacker injects malicious poisoned data into the training dataset to affect the trained model's output. Our evaluation focuses on backdoor attacks against deep neural networks trained to perform image classification using the GTSRB and CIFAR-10 datasets. Our results show that (1) these attacks produce poisoned datasets in which the poisoned and clean data are incompatible and (2) our technique successfully identifies (and removes) the poisoned data. In an end-to-end evaluation, our defense reduces the attack success rate to below 1% on 134 out of 165 scenarios, with only a 2% drop in clean accuracy on CIFAR-10 and a negligible drop in clean accuracy on GTSRB.

We study the task of training regression models with the guarantee of _label_ differential privacy (DP). Based on a global prior distribution of label values, which could be obtained privately, we derive a label DP randomization mechanism that is optimal under a given regression loss function. We prove that the optimal mechanism takes the form of a "randomized response on bins", and propose an efficient algorithm for finding the optimal bin values. We carry out a thorough experimental evaluation on several datasets demonstrating the efficacy of our algorithm.

Indiscriminate data poisoning attacks are quite effective against supervised learning. However, not much is known about their impact on unsupervised contrastive learning (CL). This paper is the first to consider indiscriminate poisoning attacks of contrastive learning. We propose Contrastive Poisoning (CP), the first effective such attack on CL. We empirically show that Contrastive Poisoning, not only drastically reduces the performance of CL algorithms, but also attacks supervised learning models, making it the most generalizable indiscriminate poisoning attack. We also show that CL algorithms with a momentum encoder are more robust to indiscriminate poisoning, and propose a new countermeasure based on matrix completion. Code is available at: https://github.com/kaiwenzha/contrastive-poisoning.

We consider the standard $K$-armed bandit problem under a distributed trust model of differential privacy (DP), which enables to guarantee privacy without a trustworthy server. Under this trust model, previous work largely focus on achieving privacy using a shuffle protocol, where a batch of users data are randomly permuted before sending to a central server. This protocol achieves ($\epsilon,\delta$) or approximate-DP guarantee by sacrificing an additive $O\!\left(\!\frac{K\log T\sqrt{\log(1/\delta)}}{\epsilon}\!\right)\!$ factor in $T$-step cumulative regret. In contrast, the optimal privacy cost to achieve a stronger ($\epsilon,0$) or pure-DP guarantee under the widely used central trust model is only $\Theta\!\left(\!\frac{K\log T}{\epsilon}\!\right)\!$, where, however, a trusted server is required. In this work, we aim to obtain a pure-DP guarantee under distributed trust model while sacrificing no more regret than that under central trust model. We achieve this by designing a generic bandit algorithm based on successive arm elimination, where privacy is guaranteed by corrupting rewards with an equivalent discrete Laplace noise ensured by a secure computation protocol. We also show that our algorithm, when instantiated with Skellam noise and the secure protocol, ensures \emph{R\'{e}nyi differential privacy} -- a stronger notion than approximate DP -- under distributed trust model with a privacy cost of $O\!\left(\!\frac{K\sqrt{\log T}}{\epsilon}\!\right)\!$. Finally, as a by-product of our techniques, we also recover the best-known regret bounds for bandits under central and local models while using only \emph{discrete privacy noise}, which can avoid the privacy leakage due to floating point arithmetic of continuous noise on finite computers.

This work studies the threats of adversarial attack on multivariate probabilistic forecasting models and viable defense mechanisms. Our studies discover a new attack pattern that negatively impact the forecasting of a target time series via making strategic, sparse (imperceptible) modifications to the past observations of a small number of other time series. To mitigate the impact of such attack, we have developed two defense strategies. First, we extend a previously developed randomized smoothing technique in classification to multivariate forecasting scenarios. Second, we develop an adversarial training algorithm that learns to create adversarial examples and at the same time optimizes the forecasting model to improve its robustness against such adversarial simulation. Extensive experiments on real-world datasets confirm that our attack schemes are powerful and our defense algorithms are more effective compared with baseline defense mechanisms.

Model extraction attacks are proven to be a severe privacy threat to Machine Learning as a Service (MLaaS). A variety of techniques have been designed to steal a remote machine learning model with high accuracy and fidelity. However, how to extract a robust model with similar resilience against adversarial attacks is never investigated. This paper presents the first study toward this goal. We first analyze those existing extraction solutions either fail to maintain the model accuracy or model robustness or lead to the robust overfitting issue. Then we propose Boundary Entropy Searching Thief (BEST), a novel model extraction attack to achieve both accuracy and robustness extraction under restricted attack budgets. BEST generates a new kind of uncertain examples for querying and reconstructing the victim model. These samples have uniform confidence scores across different classes, which can perfectly balance the trade-off between model accuracy and robustness. Extensive experiments demonstrate that BEST outperforms existing attack methods over different datasets and model architectures under limited data. It can also effectively invalidate state-of-the-art extraction defenses.

The transferability of adversarial examples across deep neural networks (DNNs) is the crux of many black-box attacks. Many prior efforts have been devoted to improving the transferability via increasing the diversity in inputs of some substitute models. In this paper, by contrast, we opt for the diversity in substitute models and advocate to attack a Bayesian model for achieving desirable transferability. Deriving from the Bayesian formulation, we develop a principled strategy for possible finetuning, which can be combined with many off-the-shelf Gaussian posterior approximations over DNN parameters. Extensive experiments have been conducted to verify the effectiveness of our method, on common benchmark datasets, and the results demonstrate that our method outperforms recent state-of-the-arts by large margins (roughly 19% absolute increase in average attack success rate on ImageNet), and, by combining with these recent methods, further performance gain can be obtained. Our code: https://github.com/qizhangli/MoreBayesian-attack.

We study a security threat to adversarial multi-armed bandit, in which an attacker perturbs the loss or reward signal to control the behavior of the victim bandit player. We show that the attacker is able to mislead any no-regret adversarial bandit algorithm into selecting a suboptimal target action in every but sublinear (T−o(T )) number of rounds, while incurring only sublinear (o(T)) cumulative attack cost. This result implies critical security concern in real-world bandit-based systems, e.g., in online recommendation, an attacker might be able to hijack the recommender system and promote a desired product. Our proposed attack algorithms require knowledge of only the regret rate, thus are agnostic to the concrete bandit algorithm employed by the victim player. We also derived a theoretical lower bound on the cumulative attack cost that any victim-agnostic attack algorithm must incur. The lower bound matches the upper bound achieved by our attack, which shows that our attack is asymptotically optimal.

As industrial applications are increasingly automated by machine learning models, enforcing personal data ownership and intellectual property rights requires tracing training data back to their rightful owners. Membership inference algorithms approach this problem by using statistical techniques to discern whether a target sample was included in a model's training set. However, existing methods only utilize the unaltered target sample or simple augmentations of the target to compute statistics. Such a sparse sampling of the model's behavior carries little information, leading to poor inference capabilities. In this work, we use adversarial tools to directly optimize for queries that are discriminative and diverse. Our improvements achieve significantly more accurate membership inference than existing methods, especially in offline scenarios and in the low false-positive regime which is critical in legal settings.

In a backdoor attack, an attacker injects corrupted examples into the training set. The goal of the attacker is to cause the final trained model to predict the attacker's desired target label when a predefined trigger is added to test inputs. Central to these attacks is the trade-off between the success rate of the attack and the number of corrupted training examples injected. We pose this attack as a novel bilevel optimization problem: construct strong poison examples that maximize the attack success rate of the trained model. We use neural tangent kernels to approximate the training dynamics of the model being attacked and automatically learn strong poison examples. We experiment on subclasses of CIFAR-10 and ImageNet with WideResNet-34 and ConvNeXt architectures on periodic and patch trigger attacks and show that NTBA-designed poisoned examples achieve, for example, an attack success rate of 90% with ten times smaller number of poison examples injected compared to the baseline. We provided an interpretation of the NTBA-designed attacks using the analysis of kernel linear regression. We further demonstrate a vulnerability in overparametrized deep neural networks, which is revealed by the shape of the neural tangent kernel.

Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized training data verbatim. This is undesirable because memorization violates privacy (exposing user data), degrades utility (repeated easy-to-memorize text is often low quality), and hurts fairness (some texts are memorized over others). We describe three log-linear relationships that quantify the degree to which LMs emit memorized training data. Memorization significantly grows as we increase (1) the capacity of a model, (2) the number of times an example has been duplicated, and (3) the number of tokens of context used to prompt the model. Surprisingly, we find the situation becomes complicated when generalizing these results across model families. On the whole, we find that memorization in LMs is more prevalent than previously believed and will likely get worse as models continues to scale, at least without active mitigations.

This work considers the challenge of performing membership inference attacks in a federated learning setting ---for image classification--- where an adversary can only observe the communication between the central node and a single client (a passive white-box attack). Passive attacks are one of the hardest-to-detect attacks, since they can be performed without modifying how the behavior of the central server or its clients, and assumes *no access to private data instances*. The key insight of our method is empirically observing that, near parameters that generalize well in test, the gradient of large overparameterized neural network models statistically behave like high-dimensional independent isotropic random vectors. Using this insight, we devise two attacks that are often little impacted by existing and proposed defenses. Finally, we validated the hypothesis that our attack depends on the overparametrization by showing that increasing the level of overparametrization (without changing the neural network architecture) positively correlates with our attack effectiveness.

Federated Learning (FL) is a setting for training machine learning models in distributed environments where the clients do not share their raw data but instead send model updates to a server. However, model updates can be subject to attacks and leak private information. Differential Privacy (DP) is a leading mitigation strategy which involves adding noise to clipped model updates, trading off performance for strong theoretical privacy guarantees. Previous work has shown that the threat model of DP is conservative and that the obtained guarantees may be vacuous or may overestimate information leakage in practice. In this paper, we aim to achieve a tighter measurement of the model exposure by considering a realistic threat model. We propose a novel method, CANIFE, that uses canaries - carefully crafted samples by a strong adversary to evaluate the empirical privacy of a training round. We apply this attack to vision models trained on CIFAR-10 and CelebA and to language models trained on Sent140 and Shakespeare. In particular, in realistic FL scenarios, we demonstrate that the empirical per-round epsilon obtained with CANIFE is 4 -- 5$\times$ lower than the theoretical bound.

Individual privacy accounting enables bounding differential privacy (DP) loss individually for each participant involved in the analysis. This can be informative as often the individual privacy losses are considerably smaller than those indicated by the DP bounds that are based on considering worst-case bounds at each data access. In order to account for the individual losses in a principled manner, we need a privacy accountant for adaptive compositions of mechanisms, where the loss incurred at a given data access is allowed to be smaller than the worst-case loss. This kind of analysis has been carried out for the Rényi differential privacy by Feldman and Zrnic (2021), however not yet for the so-called optimal privacy accountants. We make first steps in this direction by providing a careful analysis using the Gaussian differential privacy which gives optimal bounds for the Gaussian mechanism, one of the most versatile DP mechanisms. This approach is based on determining a certain supermartingale for the hockey-stick divergence and on extending the Rényi divergence-based fully adaptive composition results by Feldman and Zrnic (2021). We also consider measuring the individual $(\varepsilon,\delta)$-privacy losses using the so-called privacy loss distributions. Using the Blackwell theorem, we can then use the results of Feldman and Zrnic (2021) to construct an approximative individual $(\varepsilon,\delta)$-accountant. We also show how to speed up the FFT-based individual DP accounting using the Plancherel theorem.

A distinguishing characteristic of federated learning is that the (local) client data could have statistical heterogeneity. This heterogeneity has motivated the design of personalized learning, where individual (personalized) models are trained, through collaboration. There have been various personalization methods proposed in literature, with seemingly very different forms and methods ranging from use of a single global model for local regularization and model interpolation, to use of multiple global models for personalized clustering, etc. In this work, we begin with a statistical framework that unifies several different algorithms as well as suggest new algorithms. We apply our framework to personalized estimation, and connect it to the classical empirical Bayes' methodology. We develop novel private personalized estimation under this framework. We then use our statistical framework to propose new personalized learning algorithms, including AdaPeD based on information-geometry regularization, which numerically outperforms several known algorithms. We develop privacy for personalized learning methods with guarantees for user-level privacy and composition. We numerically evaluate the performance as well as the privacy for both the estimation and learning problems, demonstrating the advantages of our proposed methods.