arXiv subjects

Florian Tramèr

Publications and source records attributed to Florian Tramèr.

86 records · Page 5Linked to original sources

arXiv2022

What Does it Mean for a Language Model to Preserve Privacy?

Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context and sensitivity of text, and tend to memorize phrases present in their training sets. An adversary can exploit this tendency to extract training data. Depending on the nature of the content and the context in which this data was collected, this could violate expectations of privacy. Thus there is a growing interest in techniques for training language models that preserve privacy. In this paper, we discuss the mismatch between the narrow assumptions made by popular data protection techniques (data sanitization and differential privacy), and the broadness of natural language and of privacy as a social norm. We argue that existing protection methods cannot guarantee a generic and meaningful notion of privacy for language models. We conclude that language models should be trained on text data which was explicitly produced for public use.

stat.ML↗

arXiv2021

Antipodes of Label Differential Privacy: PATE and ALIBI

We consider the privacy-preserving machine learning (ML) setting where the trained model must satisfy differential privacy (DP) with respect to the labels of the training examples. We propose two novel approaches based on, respectively, the Laplace mechanism and the PATE framework, and demonstrate their effectiveness on standard benchmarks. While recent work by Ghazi et al. proposed Label DP schemes based on a randomized response mechanism, we argue that additive Laplace noise coupled with Bayesian inference (ALIBI) is a better fit for typical ML tasks. Moreover, we show how to achieve very strong privacy levels in some regimes, with our adaptation of the PATE framework that builds on recent advances in semi-supervised learning. We complement theoretical analysis of our algorithms' privacy guarantees with empirical evaluation of their memorization properties. Our evaluation suggests that comparing different algorithms according to their provable DP guarantees can be misleading and favor a less private algorithm with a tighter analysis. Code for implementation of algorithms and memorization attacks is available from https://github.com/facebookresearch/label_dp_antipodes.

cs.LG↗

arXiv2021

Advances and Open Problems in Federated Learning

Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.

cs.LG↗

arXiv2021

Differentially Private Learning Needs Better Features (or Much More Data)

We demonstrate that differentially private machine learning has not yet reached its "AlexNet moment" on many canonical vision tasks: linear models trained on handcrafted features significantly outperform end-to-end deep neural networks for moderate privacy budgets. To exceed the performance of handcrafted features, we show that private learning requires either much more private data, or access to features learned on public data from a similar domain. Our work introduces simple yet strong baselines for differentially private learning that can inform the evaluation of future progress in this area.

cs.LG↗

arXiv2020

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations

Adversarial examples are malicious inputs crafted to induce misclassification. Commonly studied sensitivity-based adversarial examples introduce semantically-small changes to an input that result in a different model prediction. This paper studies a complementary failure mode, invariance-based adversarial examples, that introduce minimal semantic changes that modify an input's true label yet preserve the model's prediction. We demonstrate fundamental tradeoffs between these two types of adversarial examples. We show that defenses against sensitivity-based attacks actively harm a model's accuracy on invariance-based attacks, and that new approaches are needed to resist both attack types. In particular, we break state-of-the-art adversarially-trained and certifiably-robust models by generating small perturbations that the models are (provably) robust to, yet that change an input's class according to human labelers. Finally, we formally show that the existence of excessively invariant classifiers arises from the presence of overly-robust predictive features in standard datasets.

cs.LG↗

arXiv2020

SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems

SentiNet is a novel detection framework for localized universal attacks on neural networks. These attacks restrict adversarial noise to contiguous portions of an image and are reusable with different images -- constraints that prove useful for generating physically-realizable attacks. Unlike most other works on adversarial detection, SentiNet does not require training a model or preknowledge of an attack prior to detection. Our approach is appealing due to the large number of possible mechanisms and attack-vectors that an attack-specific defense would have to consider. By leveraging the neural network's susceptibility to attacks and by using techniques from model interpretability and object detection as detection mechanisms, SentiNet turns a weakness of a model into a strength. We demonstrate the effectiveness of SentiNet on three different attacks -- i.e., data poisoning attacks, trojaned networks, and adversarial patches (including physically realizable attacks) -- and show that our defense is able to achieve very competitive performance metrics for all three threats. Finally, we show that SentiNet is robust against strong adaptive adversaries, who build adversarial patches that specifically target the components of SentiNet's architecture.

cs.CR↗

arXiv2020

Ensemble Adversarial Training: Attacks and Defenses

Adversarial examples are perturbed inputs designed to fool machine learning models. Adversarial training injects such examples into training data to increase robustness. To scale this technique to large datasets, perturbations are crafted using fast single-step methods that maximize a linear approximation of the model's loss. We show that this form of adversarial training converges to a degenerate global minimum, wherein small curvature artifacts near the data points obfuscate a linear approximation of the loss. The model thus learns to generate weak perturbations, rather than defend against strong ones. As a result, we find that adversarial training remains vulnerable to black-box attacks, where we transfer perturbations computed on undefended models, as well as to a powerful novel single-step attack that escapes the non-smooth vicinity of the input data via a small random step. We further introduce Ensemble Adversarial Training, a technique that augments training data with perturbations transferred from other models. On ImageNet, Ensemble Adversarial Training yields models with strong robustness to black-box attacks. In particular, our most robust model won the first round of the NIPS 2017 competition on Defenses against Adversarial Attacks. However, subsequent work found that more elaborate black-box attacks could significantly enhance transferability and reduce the accuracy of our models.

stat.ML↗

arXiv2019

Adversarial Training and Robustness for Multiple Perturbations

Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small $\ell_\infty$-noise). For other perturbations, these defenses offer no guarantees and, at times, even increase the model's vulnerability. Our aim is to understand the reasons underlying this robustness trade-off, and to train models that are simultaneously robust to multiple perturbation types. We prove that a trade-off in robustness to different types of $\ell_p$-bounded and spatial perturbations must exist in a natural and simple statistical setting. We corroborate our formal analysis by demonstrating similar robustness trade-offs on MNIST and CIFAR10. Building upon new multi-perturbation adversarial training schemes, and a novel efficient attack for finding $\ell_1$-bounded adversarial examples, we show that no model trained against multiple attacks achieves robustness competitive with that of models trained on each attack individually. In particular, we uncover a pernicious gradient-masking phenomenon on MNIST, which causes adversarial training with first-order $\ell_\infty, \ell_1$ and $\ell_2$ adversaries to achieve merely $50\%$ accuracy. Our results question the viability and computational scalability of extending adversarial robustness, and adversarial training, to multiple perturbation types.

cs.LG↗

arXiv2019

AdVersarial: Perceptual Ad Blocking meets Adversarial Machine Learning

Perceptual ad-blocking is a novel approach that detects online advertisements based on their visual content. Compared to traditional filter lists, the use of perceptual signals is believed to be less prone to an arms race with web publishers and ad networks. We demonstrate that this may not be the case. We describe attacks on multiple perceptual ad-blocking techniques, and unveil a new arms race that likely disfavors ad-blockers. Unexpectedly, perceptual ad-blocking can also introduce new vulnerabilities that let an attacker bypass web security boundaries and mount DDoS attacks. We first analyze the design space of perceptual ad-blockers and present a unified architecture that incorporates prior academic and commercial work. We then explore a variety of attacks on the ad-blocker's detection pipeline, that enable publishers or ad networks to evade or detect ad-blocking, and at times even abuse its high privilege level to bypass web security boundaries. On one hand, we show that perceptual ad-blocking must visually classify rendered web content to escape an arms race centered on obfuscation of page markup. On the other, we present a concrete set of attacks on visual ad-blockers by constructing adversarial examples in a real web page context. For seven ad-detectors, we create perturbed ads, ad-disclosure logos, and native web content that misleads perceptual ad-blocking with 100% success rates. In one of our attacks, we demonstrate how a malicious user can upload adversarial content, such as a perturbed image in a Facebook post, that fools the ad-blocker into removing another users' non-ad content. Moving beyond the Web and visual domain, we also build adversarial examples for AdblockRadio, an open source radio client that uses machine learning to detects ads in raw audio streams.

cs.CR↗

arXiv2019

Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness

Adversarial examples are malicious inputs crafted to cause a model to misclassify them. Their most common instantiation, "perturbation-based" adversarial examples introduce changes to the input that leave its true label unchanged, yet result in a different model prediction. Conversely, "invariance-based" adversarial examples insert changes to the input that leave the model's prediction unaffected despite the underlying input's label having changed. In this paper, we demonstrate that robustness to perturbation-based adversarial examples is not only insufficient for general robustness, but worse, it can also increase vulnerability of the model to invariance-based adversarial examples. In addition to analytical constructions, we empirically study vision classifiers with state-of-the-art robustness to perturbation-based adversaries constrained by an $\ell_p$ norm. We mount attacks that exploit excessive model invariance in directions relevant to the task, which are able to find adversarial examples within the $\ell_p$ ball. In fact, we find that classifiers trained to be $\ell_p$-norm robust are more vulnerable to invariance-based adversarial examples than their undefended counterparts. Excessive invariance is not limited to models trained to be robust to perturbation-based $\ell_p$-norm adversaries. In fact, we argue that the term adversarial example is used to capture a series of model limitations, some of which may not have been discovered yet. Accordingly, we call for a set of precise definitions that taxonomize and address each of these shortcomings in learning.

cs.LG↗

arXiv2019

Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware

As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environments (TEEs), which use hardware and software protections to isolate sensitive computations from the untrusted software stack. However, these isolation guarantees come at a price in performance, compared to untrusted alternatives. This paper initiates the study of high performance execution of Deep Neural Networks (DNNs) in TEEs by efficiently partitioning DNN computations between trusted and untrusted devices. Building upon an efficient outsourcing scheme for matrix multiplication, we propose Slalom, a framework that securely delegates execution of all linear layers in a DNN from a TEE (e.g., Intel SGX or Sanctum) to a faster, yet untrusted, co-located processor. We evaluate Slalom by running DNNs in an Intel SGX enclave, which selectively delegates work to an untrusted GPU. For canonical DNNs (VGG16, MobileNet and ResNet variants) we obtain 6x to 20x increases in throughput for verifiable inference, and 4x to 11x for verifiable and private inference.

stat.ML↗

arXiv2017

The Space of Transferable Adversarial Examples

Adversarial examples are maliciously perturbed inputs designed to mislead machine learning (ML) models at test-time. They often transfer: the same adversarial example fools more than one model. In this work, we propose novel methods for estimating the previously unknown dimensionality of the space of adversarial inputs. We find that adversarial examples span a contiguous subspace of large (~25) dimensionality. Adversarial subspaces with higher dimensionality are more likely to intersect. We find that for two different models, a significant fraction of their subspaces is shared, thus enabling transferability. In the first quantitative analysis of the similarity of different models' decision boundaries, we show that these boundaries are actually close in arbitrary directions, whether adversarial or benign. We conclude by formally studying the limits of transferability. We derive (1) sufficient conditions on the data distribution that imply transferability for simple model classes and (2) examples of scenarios in which transfer does not occur. These findings indicate that it may be possible to design defenses against transfer-based attacks, even for models that are vulnerable to direct attacks.

stat.ML↗

arXiv2016

Stealing Machine Learning Models via Prediction APIs

Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query interfaces. ML-as-a-service ("predictive analytics") systems are an example: Some allow users to train models on potentially sensitive data and charge others for access on a pay-per-query basis. The tension between model confidentiality and public access motivates our investigation of model extraction attacks. In such attacks, an adversary with black-box access, but no prior knowledge of an ML model's parameters or training data, aims to duplicate the functionality of (i.e., "steal") the model. Unlike in classical learning theory settings, ML-as-a-service offerings may accept partial feature vectors as inputs and include confidence values with predictions. Given these practices, we show simple, efficient attacks that extract target ML models with near-perfect fidelity for popular model classes including logistic regression, neural networks, and decision trees. We demonstrate these attacks against the online services of BigML and Amazon Machine Learning. We further show that the natural countermeasure of omitting confidence values from model outputs still admits potentially harmful model extraction attacks. Our results highlight the need for careful ML model deployment and new model extraction countermeasures.

cs.CR↗

arXiv2016

FairTest: Discovering Unwarranted Associations in Data-Driven Applications

In a world where traditional notions of privacy are increasingly challenged by the myriad companies that collect and analyze our data, it is important that decision-making entities are held accountable for unfair treatments arising from irresponsible data usage. Unfortunately, a lack of appropriate methodologies and tools means that even identifying unfair or discriminatory effects can be a challenge in practice. We introduce the unwarranted associations (UA) framework, a principled methodology for the discovery of unfair, discriminatory, or offensive user treatment in data-driven applications. The UA framework unifies and rationalizes a number of prior attempts at formalizing algorithmic fairness. It uniquely combines multiple investigative primitives and fairness metrics with broad applicability, granular exploration of unfair treatment in user subgroups, and incorporation of natural notions of utility that may account for observed disparities. We instantiate the UA framework in FairTest, the first comprehensive tool that helps developers check data-driven applications for unfair user treatment. It enables scalable and statistically rigorous investigation of associations between application outcomes (such as prices or premiums) and sensitive user attributes (such as race or gender). Furthermore, FairTest provides debugging capabilities that let programmers rule out potential confounders for observed unfair effects. We report on use of FairTest to investigate and in some cases address disparate impact, offensive labeling, and uneven rates of algorithmic error in four data-driven applications. As examples, our results reveal subtle biases against older populations in the distribution of error in a predictive health application and offensive racial labeling in an image tagger.

cs.CY↗