arXiv subjects

Somesh Jha

Publications and source records attributed to Somesh Jha.

At least 109 records · Page 6Linked to original sources

arXiv2020

Face-Off: Adversarial Face Obfuscation

Advances in deep learning have made face recognition technologies pervasive. While useful to social media platforms and users, this technology carries significant privacy threats. Coupled with the abundant information they have about users, service providers can associate users with social interactions, visited places, activities, and preferences--some of which the user may not want to share. Additionally, facial recognition models used by various agencies are trained by data scraped from social media platforms. Existing approaches to mitigate these privacy risks from unwanted face recognition result in an imbalanced privacy-utility trade-off to users. In this paper, we address this trade-off by proposing Face-Off, a privacy-preserving framework that introduces strategic perturbations to the user's face to prevent it from being correctly recognized. To realize Face-Off, we overcome a set of challenges related to the black-box nature of commercial face recognition services, and the scarcity of literature for adversarial attacks on metric networks. We implement and evaluate Face-Off to find that it deceives three commercial face recognition services from Microsoft, Amazon, and Face++. Our user study with 423 participants further shows that the perturbations come at an acceptable cost for the users.

cs.CR↗

arXiv2020

Improving Utility and Security of the Shuffler-based Differential Privacy

When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the central aggregator. LDP imposes large amount of noise as each user executes the randomization independently. To address this issue, recent work introduced an intermediate server with the assumption that this intermediate server does not collude with the aggregator. Under this assumption, less noise can be added to achieve the same privacy guarantee as LDP, thus improving utility for the data collection task. This paper investigates this multiple-party setting of LDP. We analyze the system model and identify potential adversaries. We then make two improvements: a new algorithm that achieves a better privacy-utility tradeoff; and a novel protocol that provides better protection against various attacks. Finally, we perform experiments to compare different methods and demonstrate the benefits of using our proposed method.

cs.CR↗

arXiv2020

Analyzing and Improving Neural Networks by Generating Semantic Counterexamples through Differentiable Rendering

Even as deep neural networks (DNNs) have achieved remarkable success on vision-related tasks, their performance is brittle to transformations in the input. Of particular interest are semantic transformations that model changes that have a basis in the physical world, such as rotations, translations, changes in lighting or camera pose. In this paper, we show how differentiable rendering can be utilized to generate images that are informative, yet realistic, and which can be used to analyze DNN performance and improve its robustness through data augmentation. Given a differentiable renderer and a DNN, we show how to use off-the-shelf attacks from adversarial machine learning to generate semantic counterexamples -- images where semantic features are changed as to produce misclassifications or misdetections. We validate our approach on DNNs for image classification and object detection. For classification, we show that semantic counterexamples, when used to augment the dataset, (i) improve generalization performance (ii) enhance robustness to semantic transformations, and (iii) transfer between models. Additionally, in comparison to sampling-based semantic augmentation, our technique generates more informative data in a sample efficient manner.

cs.LG↗

arXiv2020

Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models

Directed graphical models (DGMs) are a class of probabilistic models that are widely used for predictive analysis in sensitive domains, such as medical diagnostics. In this paper we present an algorithm for differentially private learning of the parameters of a DGM with a publicly known graph structure over fully observed data. Our solution optimizes for the utility of inference queries over the DGM and \textit{adds noise that is customized to the properties of the private input dataset and the graph structure of the DGM}. To the best of our knowledge, this is the first explicit data-dependent privacy budget allocation algorithm for DGMs. We compare our algorithm with a standard data-independent approach over a diverse suite of DGM benchmarks and demonstrate that our solution requires a privacy budget that is $3\times$ smaller to obtain the same or higher utility.

cs.LG↗

arXiv2020

Concise Explanations of Neural Networks using Adversarial Training

We show new connections between adversarial learning and explainability for deep neural networks (DNNs). One form of explanation of the output of a neural network model in terms of its input features, is a vector of feature-attributions. Two desirable characteristics of an attribution-based explanation are: (1) $\textit{sparseness}$: the attributions of irrelevant or weakly relevant features should be negligible, thus resulting in $\textit{concise}$ explanations in terms of the significant features, and (2) $\textit{stability}$: it should not vary significantly within a small local neighborhood of the input. Our first contribution is a theoretical exploration of how these two properties (when using attributions based on Integrated Gradients, or IG) are related to adversarial training, for a class of 1-layer networks (which includes logistic regression models for binary and multi-class classification); for these networks we show that (a) adversarial training using an $\ell_\infty$-bounded adversary produces models with sparse attribution vectors, and (b) natural model-training while encouraging stable explanations (via an extra term in the loss function), is equivalent to adversarial training. Our second contribution is an empirical verification of phenomenon (a), which we show, somewhat surprisingly, occurs $\textit{not only}$ $\textit{in 1-layer networks}$, $\textit{but also DNNs}$ $\textit{trained on }$ $\textit{standard image datasets}$, and extends beyond IG-based attributions, to those based on DeepSHAP: adversarial training with $\ell_\infty$-bounded perturbations yields significantly sparser attribution vectors, with little degradation in performance on natural test data, compared to natural training. Moreover, the sparseness of the attribution vectors is significantly better than that achievable via $\ell_1$-regularized natural training.

cs.LG↗

arXiv2020

Semantic Robustness of Models of Source Code

Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to source-code modifications that preserve code functionality. (1) We define a powerful adversary that can employ sequences of parametric, semantics-preserving program transformations; (2) we show how to perform adversarial training to learn models robust to such adversaries; (3) we conduct an evaluation on different languages and architectures, demonstrating significant quantitative gains in robustness.

cs.LG↗

arXiv2020

Representation Bayesian Risk Decompositions and Multi-Source Domain Adaptation

We consider representation learning (hypothesis class $\mathcal{H} = \mathcal{F}\circ\mathcal{G}$) where training and test distributions can be different. Recent studies provide hints and failure examples for domain invariant representation learning, a common approach for this problem, but the explanations provided are somewhat different and do not provide a unified picture. In this paper, we provide new decompositions of risk which give finer-grained explanations and clarify potential generalization issues. For Single-Source Domain Adaptation, we give an exact decomposition (an equality) of the target risk, via a natural hybrid argument, as sum of three factors: (1) source risk, (2) representation conditional label divergence, and (3) representation covariate shift. We derive a similar decomposition for the Multi-Source case. These decompositions reveal factors (2) and (3) as the precise reasons for failure to generalize. For example, we demonstrate that domain adversarial neural networks (DANN) attempt to regularize for (3) but miss (2), while a recent technique Invariant Risk Minimization (IRM) attempts to account for (2) but does not consider (3). We also verify our observations experimentally.

cs.LG↗

arXiv2020

Towards Effective Differential Privacy Communication for Users' Data Sharing Decision and Comprehension

Differential privacy protects an individual's privacy by perturbing data on an aggregated level (DP) or individual level (LDP). We report four online human-subject experiments investigating the effects of using different approaches to communicate differential privacy techniques to laypersons in a health app data collection setting. Experiments 1 and 2 investigated participants' data disclosure decisions for low-sensitive and high-sensitive personal information when given different DP or LDP descriptions. Experiments 3 and 4 uncovered reasons behind participants' data sharing decisions, and examined participants' subjective and objective comprehensions of these DP or LDP descriptions. When shown descriptions that explain the implications instead of the definition/processes of DP or LDP technique, participants demonstrated better comprehension and showed more willingness to share information with LDP than with DP, indicating their understanding of LDP's stronger privacy guarantee compared with DP.

cs.CR↗

arXiv2020

Crypt$ε$: Crypto-Assisted Differential Privacy on Untrusted Servers

Differential privacy (DP) has steadily become the de-facto standard for achieving privacy in data analysis, which is typically implemented either in the "central" or "local" model. The local model has been more popular for commercial deployments as it does not require a trusted data collector. This increased privacy, however, comes at a cost of utility and algorithmic expressibility as compared to the central model. In this work, we propose, Crypt$ε$, a system and programming framework that (1) achieves the accuracy guarantees and algorithmic expressibility of the central model (2) without any trusted data collector like in the local model. Crypt$ε$ achieves the "best of both worlds" by employing two non-colluding untrusted servers that run DP programs on encrypted data from the data owners. Although straightforward implementations of DP programs using secure computation tools can achieve the above goal theoretically, in practice they are beset with many challenges such as poor performance and tricky security proofs. To this end, Crypt$ε$ allows data analysts to author logical DP programs that are automatically translated to secure protocols that work on encrypted data. These protocols ensure that the untrusted servers learn nothing more than the noisy outputs, thereby guaranteeing DP (for computationally bounded adversaries) for all Crypt$ε$ programs. Crypt$ε$ supports a rich class of DP programs that can be expressed via a small set of transformation and measurement operators followed by arbitrary post-processing. Further, we propose performance optimizations leveraging the fact that the output is noisy. We demonstrate Crypt$ε$'s feasibility for practical DP analysis with extensive empirical evaluations on real datasets.

cs.CR↗

arXiv2020

Analyzing Accuracy Loss in Randomized Smoothing Defenses

Recent advances in machine learning (ML) algorithms, especially deep neural networks (DNNs), have demonstrated remarkable success (sometimes exceeding human-level performance) on several tasks, including face and speech recognition. However, ML algorithms are vulnerable to \emph{adversarial attacks}, such test-time, training-time, and backdoor attacks. In test-time attacks an adversary crafts adversarial examples, which are specially crafted perturbations imperceptible to humans which, when added to an input example, force a machine learning model to misclassify the given input example. Adversarial examples are a concern when deploying ML algorithms in critical contexts, such as information security and autonomous driving. Researchers have responded with a plethora of defenses. One promising defense is \emph{randomized smoothing} in which a classifier's prediction is smoothed by adding random noise to the input example we wish to classify. In this paper, we theoretically and empirically explore randomized smoothing. We investigate the effect of randomized smoothing on the feasible hypotheses space, and show that for some noise levels the set of hypotheses which are feasible shrinks due to smoothing, giving one reason why the natural accuracy drops after smoothing. To perform our analysis, we introduce a model for randomized smoothing which abstracts away specifics, such as the exact distribution of the noise. We complement our theoretical results with extensive experiments.

cs.LG↗

arXiv2020

An Investigation of Data Poisoning Defenses for Online Learning

Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of prior work has developed attacks and defenses, there is not much general understanding on when various attacks and defenses are effective. In this work, we undertake a rigorous study of defenses against data poisoning for online learning. First, we study four standard defenses in a powerful threat model, and provide conditions under which they can allow or resist rapid poisoning. We then consider a weaker and more realistic threat model, and show that the success of the adversary in the presence of data poisoning defenses there depends on the "ease" of the learning problem.

cs.LG↗

arXiv2020

CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods

We study the problem of learning Granger causality between event types from asynchronous, interdependent, multi-type event sequences. Existing work suffers from either limited model flexibility or poor model explainability and thus fails to uncover Granger causality across a wide variety of event sequences with diverse event interdependency. To address these weaknesses, we propose CAUSE (Causality from AttribUtions on Sequence of Events), a novel framework for the studied task. The key idea of CAUSE is to first implicitly capture the underlying event interdependency by fitting a neural point process, and then extract from the process a Granger causality statistic using an axiomatic attribution method. Across multiple datasets riddled with diverse event interdependency, we demonstrate that CAUSE achieves superior performance on correctly inferring the inter-type Granger causality over a range of state-of-the-art methods.

cs.LG↗

arXiv2020

On the Need for Topology-Aware Generative Models for Manifold-Based Defenses

Machine-learning (ML) algorithms or models, especially deep neural networks (DNNs), have shown significant promise in several areas. However, researchers have recently demonstrated that ML algorithms, especially DNNs, are vulnerable to adversarial examples (slightly perturbed samples that cause misclassification). The existence of adversarial examples has hindered the deployment of ML algorithms in safety-critical sectors, such as security. Several defenses for adversarial examples exist in the literature. One of the important classes of defenses are manifold-based defenses, where a sample is ``pulled back" into the data manifold before classifying. These defenses rely on the assumption that data lie in a manifold of a lower dimension than the input space. These defenses use a generative model to approximate the input distribution. In this paper, we investigate the following question: do the generative models used in manifold-based defenses need to be topology-aware? We suggest the answer is yes, and we provide theoretical and empirical evidence to support our claim.

cs.LG↗

arXiv2019

Adversarially Robust Learning Could Leverage Computational Hardness

Over recent years, devising classification algorithms that are robust to adversarial perturbations has emerged as a challenging problem. In particular, deep neural nets (DNNs) seem to be susceptible to small imperceptible changes over test instances. However, the line of work in provable robustness, so far, has been focused on information-theoretic robustness, ruling out even the existence of any adversarial examples. In this work, we study whether there is a hope to benefit from algorithmic nature of an attacker that searches for adversarial examples, and ask whether there is any learning task for which it is possible to design classifiers that are only robust against polynomial-time adversaries. Indeed, numerous cryptographic tasks can only be secure against computationally bounded adversaries, and are indeed impossible for computationally unbounded attackers. Thus, it is natural to ask if the same strategy could help robust learning. We show that computational limitation of attackers can indeed be useful in robust learning by demonstrating the possibility of a classifier for some learning task for which computational and information theoretic adversaries of bounded perturbations have very different power. Namely, while computationally unbounded adversaries can attack successfully and find adversarial examples with small perturbation, polynomial time adversaries are unable to do so unless they can break standard cryptographic hardness assumptions. Our results, therefore, indicate that perhaps a similar approach to cryptography (relying on computational hardness) holds promise for achieving computationally robust machine learning. On the reverse directions, we also show that the existence of such learning task in which computational robustness beats information theoretic robustness requires computational hardness by implying (average-case) hardness of NP.

cs.LG↗

arXiv2019

Rearchitecting Classification Frameworks For Increased Robustness

While generalizing well over natural inputs, neural networks are vulnerable to adversarial inputs. Existing defenses against adversarial inputs have largely been detached from the real world. These defenses also come at a cost to accuracy. Fortunately, there are invariances of an object that are its salient features; when we break them it will necessarily change the perception of the object. We find that applying invariants to the classification task makes robustness and accuracy feasible together. Two questions follow: how to extract and model these invariances? and how to design a classification paradigm that leverages these invariances to improve the robustness accuracy trade-off? The remainder of the paper discusses solutions to the aformenetioned questions.

cs.LG↗

arXiv2019

Exploring Connections Between Active Learning and Model Extraction

Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the model, and (b) a user-friendly query interface to access the model. However, such MLaaS systems raise privacy concerns such as model extraction. In model extraction attacks, adversaries maliciously exploit the query interface to steal the model. More precisely, in a model extraction attack, a good approximation of a sensitive or proprietary model held by the server is extracted (i.e. learned) by a dishonest user who interacts with the server only via the query interface. This attack was introduced by Tramer et al. at the 2016 USENIX Security Symposium, where practical attacks for various models were shown. We believe that better understanding the efficacy of model extraction attacks is paramount to designing secure MLaaS systems. To that end, we take the first step by (a) formalizing model extraction and discussing possible defense strategies, and (b) drawing parallels between model extraction and established area of active learning. In particular, we show that recent advancements in the active learning domain can be used to implement powerful model extraction attacks, and investigate possible defense strategies.

cs.LG↗

arXiv2019

Robust Attribution Regularization

An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions. We take a step towards solving this problem through the lens of axiomatic attribution of neural networks. Our theory is grounded in the recent work, Integrated Gradients (IG), in axiomatically attributing a neural network's output change to its input change. We propose training objectives in classic robust optimization models to achieve robust IG attributions. Our objectives give principled generalizations of previous objectives designed for robust predictions, and they naturally degenerate to classic soft-margin training for one-layer neural networks. We also generalize previous theory and prove that the objectives for different robust optimization models are closely related. Experiments demonstrate the effectiveness of our method, and also point to intriguing problems which hint at the need for better optimization techniques or better neural network architectures for robust attribution training.

cs.LG↗

arXiv2019

Towards Understanding Limitations of Pixel Discretization Against Adversarial Attacks

Wide adoption of artificial neural networks in various domains has led to an increasing interest in defending adversarial attacks against them. Preprocessing defense methods such as pixel discretization are particularly attractive in practice due to their simplicity, low computational overhead, and applicability to various systems. It is observed that such methods work well on simple datasets like MNIST, but break on more complicated ones like ImageNet under recently proposed strong white-box attacks. To understand the conditions for success and potentials for improvement, we study the pixel discretization defense method, including more sophisticated variants that take into account the properties of the dataset being discretized. Our results again show poor resistance against the strong attacks. We analyze our results in a theoretical framework and offer strong evidence that pixel discretization is unlikely to work on all but the simplest of the datasets. Furthermore, our arguments present insights why some other preprocessing defenses may be insecure.

cs.CR↗