arXiv subjects

Somesh Jha

Publications and source records attributed to Somesh Jha.

At least 127 records · Page 7Linked to original sources

arXiv2019

OAT: Attesting Operation Integrity of Embedded Devices

Due to the wide adoption of IoT/CPS systems, embedded devices(IoT frontends) become increasingly connected and mission-critical, which in turn has attracted advanced attacks (e.g., control-flow hijacks and data-only attacks). Unfortunately, IoT backends are unable to detect if such attacks have happened while receiving data, service requests, or operation status from IoT devices. As a result, currently, IoT backends are forced to blindly trust the IoT devices that they interact with. To fill this void, we first formulate a new security property for embedded devices, called "Operation Execution Integrity" or OEI. We then design and build a system, OAT, that enables remote OEI attestation for ARM-based bare-metal embedded devices. Our formulation of OEI captures the integrity of both control flow and critical data involved in an operation execution. Therefore, satisfying OEI entails that an operation execution is free of unexpected control and data manipulations, which existing attestation methods cannot check. Our design of OAT strikes a balance between prover's constraints (embedded devices' limited computing power and storage) and verifier's requirements(complete verifiability and forensic assistance). OAT uses a new control-flow measurement scheme, which enables light-weight and space-efficient collection of measurements (97% space reduction from the trace-based approach). OAT performs the remote control-flow verification through abstract execution, which is fast and deterministic. OAT also features lightweight integrity checking for critical data (74% fewer instrumentation needed than previous work). Our security analysis shows that OAT allows remote verifiers or IoT backends to detect both control-flow hijacks and data-only attacks that affect the execution of operations on IoT devices. In our evaluation using real embedded programs, OAT incurs a runtime overhead of 2.7%.

cs.CR↗

arXiv2019

Analyzing the Robustness of Nearest Neighbors to Adversarial Examples

Motivated by safety-critical applications, test-time attacks on classifiers via adversarial examples has recently received a great deal of attention. However, there is a general lack of understanding on why adversarial examples arise; whether they originate due to inherent properties of data or due to lack of training samples remains ill-understood. In this work, we introduce a theoretical framework analogous to bias-variance theory for understanding these effects. We use our framework to analyze the robustness of a canonical non-parametric classifier - the k-nearest neighbors. Our analysis shows that its robustness properties depend critically on the value of k - the classifier may be inherently non-robust for small k, but its robustness approaches that of the Bayes Optimal classifier for fast-growing k. We propose a novel modified 1-nearest neighbor classifier, and guarantee its robustness in the large sample limit. Our experiments suggest that this classifier may have good robustness properties even for reasonable data set sizes.

stat.ML↗

arXiv2019

Attribution-driven Causal Analysis for Detection of Adversarial Examples

Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input by incrementally masking high attribution features. We study the robustness of machine learning models on benign and adversarial inputs in this neighborhood. Our study indicates that benign inputs are robust to the masking of high attribution features but adversarial inputs generated by the state-of-the-art adversarial attack methods such as DeepFool, FGSM, CW and PGD, are not robust to such masking. Further, our study demonstrates that this concentration of high-attribution features responsible for the incorrect decision is more pronounced in physically realizable adversarial examples. This difference in attribution of benign and adversarial inputs can be used to detect adversarial examples. Such a defense approach is independent of training data and attack method, and we demonstrate its effectiveness on digital and physically realizable perturbations.

cs.LG↗

arXiv2018

Privacy-Preserving Collaborative Prediction using Random Forests

We study the problem of privacy-preserving machine learning (PPML) for ensemble methods, focusing our effort on random forests. In collaborative analysis, PPML attempts to solve the conflict between the need for data sharing and privacy. This is especially important in privacy sensitive applications such as learning predictive models for clinical decision support from EHR data from different clinics, where each clinic has a responsibility for its patients' privacy. We propose a new approach for ensemble methods: each entity learns a model, from its own data, and then when a client asks the prediction for a new private instance, the answers from all the locally trained models are used to compute the prediction in such a way that no extra information is revealed. We implement this approach for random forests and we demonstrate its high efficiency and potential accuracy benefit via experiments on real-world datasets, including actual EHR data.

cs.LG↗

arXiv2018

Adversarial Binaries for Authorship Identification

Binary code authorship identification determines authors of a binary program. Existing techniques have used supervised machine learning for this task. In this paper, we look this problem from an attacker's perspective. We aim to modify a test binary, such that it not only causes misprediction but also maintains the functionality of the original input binary. Attacks against binary code are intrinsically more difficult than attacks against domains such as computer vision, where attackers can change each pixel of the input image independently and still maintain a valid image. For binary code, even flipping one bit of a binary may cause the binary to be invalid, to crash at the run-time, or to lose the original functionality. We investigate two types of attacks: untargeted attacks, causing misprediction to any of the incorrect authors, and targeted attacks, causing misprediction to a specific one among the incorrect authors. We develop two key attack capabilities: feature vector modification, generating an adversarial feature vector that both corresponds to a real binary and causes the required misprediction, and input binary modification, modifying the input binary to match the adversarial feature vector while maintaining the functionality of the input binary. We evaluated our attack against classifiers trained with a state-of-the-art method for authorship attribution. The classifiers for authorship identification have 91% accuracy on average. Our untargeted attack has a 96% success rate on average, showing that we can effectively suppress authorship signal. Our targeted attack has a 46% success rate on average, showing that it is possible, but significantly more difficult to impersonate a specific programmer's style. Our attack reveals that existing binary code authorship identification techniques rely on code features that are easy to modify, and thus are vulnerable to attacks.

cs.CR↗

arXiv2018

Explainable Black-Box Attacks Against Model-based Authentication

Establishing unique identities for both humans and end systems has been an active research problem in the security community, giving rise to innovative machine learning-based authentication techniques. Although such techniques offer an automated method to establish identity, they have not been vetted against sophisticated attacks that target their core machine learning technique. This paper demonstrates that mimicking the unique signatures generated by host fingerprinting and biometric authentication systems is possible. We expose the ineffectiveness of underlying machine learning classification models by constructing a blind attack based around the query synthesis framework and utilizing Explainable-AI (XAI) techniques. We launch an attack in under 130 queries on a state-of-the-art face authentication system, and under 100 queries on a host authentication system. We examine how these attacks can be defended against and explore their limitations. XAI provides an effective means for adversaries to infer decision boundaries and provides a new way forward in constructing attacks against systems using machine learning models for authentication.

cs.LG↗

arXiv2018

Neural-Augmented Static Analysis of Android Communication

We address the problem of discovering communication links between applications in the popular Android mobile operating system, an important problem for security and privacy in Android. Any scalable static analysis in this complex setting is bound to produce an excessive amount of false-positives, rendering it impractical. To improve precision, we propose to augment static analysis with a trained neural-network model that estimates the probability that a communication link truly exists. We describe a neural-network architecture that encodes abstractions of communicating objects in two applications and estimates the probability with which a link indeed exists. At the heart of our architecture are type-directed encoders (TDE), a general framework for elegantly constructing encoders of a compound data type by recursively composing encoders for its constituent types. We evaluate our approach on a large corpus of Android applications, and demonstrate that it achieves very high accuracy. Further, we conduct thorough interpretability studies to understand the internals of the learned neural networks.

cs.PL↗

arXiv2018

Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training

In this paper we study leveraging confidence information induced by adversarial training to reinforce adversarial robustness of a given adversarially trained model. A natural measure of confidence is $\|F({\bf x})\|_\infty$ (i.e. how confident $F$ is about its prediction?). We start by analyzing an adversarial training formulation proposed by Madry et al.. We demonstrate that, under a variety of instantiations, an only somewhat good solution to their objective induces confidence to be a discriminator, which can distinguish between right and wrong model predictions in a neighborhood of a point sampled from the underlying distribution. Based on this, we propose Highly Confident Near Neighbor (${\tt HCNN}$), a framework that combines confidence information and nearest neighbor search, to reinforce adversarial robustness of a base model. We give algorithms in this framework and perform a detailed empirical study. We report encouraging experimental results that support our analysis, and also discuss problems we observed with existing adversarial training.

cs.LG↗

arXiv2018

Semantic Adversarial Deep Learning

Fueled by massive amounts of data, models produced by machine-learning (ML) algorithms, especially deep neural networks, are being used in diverse domains where trustworthiness is a concern, including automotive systems, finance, health care, natural language processing, and malware detection. Of particular concern is the use of ML algorithms in cyber-physical systems (CPS), such as self-driving cars and aviation, where an adversary can cause serious consequences. However, existing approaches to generating adversarial examples and devising robust ML algorithms mostly ignore the semantics and context of the overall system containing the ML component. For example, in an autonomous vehicle using deep learning for perception, not every adversarial example for the neural network might lead to a harmful consequence. Moreover, one may want to prioritize the search for adversarial examples towards those that significantly modify the desired semantics of the overall system. Along the same lines, existing algorithms for constructing robust ML algorithms ignore the specification of the overall system. In this paper, we argue that the semantics and specification of the overall system has a crucial role to play in this line of research. We present preliminary research results that support this claim.

cs.LG↗

arXiv2018

Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting

Machine learning algorithms, when applied to sensitive data, pose a distinct threat to privacy. A growing body of prior work demonstrates that models produced by these algorithms may leak specific private information in the training data to an attacker, either through the models' structure or their observable behavior. However, the underlying cause of this privacy risk is not well understood beyond a handful of anecdotal accounts that suggest overfitting and influence might play a role. This paper examines the effect that overfitting and influence have on the ability of an attacker to learn information about the training data from machine learning models, either through training set membership inference or attribute inference attacks. Using both formal and empirical analyses, we illustrate a clear relationship between these factors and the privacy risk that arises in several popular machine learning algorithms. We find that overfitting is sufficient to allow an attacker to perform membership inference and, when the target attribute meets certain conditions about its influence, attribute inference attacks. Interestingly, our formal analysis also shows that overfitting is not necessary for these attacks and begins to shed light on what other factors may be in play. Finally, we explore the connection between membership inference and attribute inference, showing that there are deep connections between the two that lead to effective new attacks.

cs.CR↗

arXiv2017

Malware Lineage in the Wild

Malware lineage studies the evolutionary relationships among malware and has important applications for malware analysis. A persistent limitation of prior malware lineage approaches is to consider every input sample a separate malware version. This is problematic since a majority of malware are packed and the packing process produces many polymorphic variants (i.e., executables with different file hash) of the same malware version. Thus, many samples correspond to the same malware version and it is challenging to identify distinct malware versions from polymorphic variants. This problem does not manifest in prior malware lineage approaches because they work on synthetic malware, malware that are not packed, or packed malware for which unpackers are available. In this work, we propose a novel malware lineage approach that works on malware samples collected in the wild. Given a set of malware executables from the same family, for which no source code is available and which may be packed, our approach produces a lineage graph where nodes are versions of the family and edges describe the relationships between versions. To enable our malware lineage approach, we propose the first technique to identify the versions of a malware family and a scalable code indexing technique for determining shared functions between any pair of input samples. We have evaluated the accuracy of our approach on 13 open-source programs and have applied it to produce lineage graphs for 10 popular malware families. Our malware lineage graphs achieve on average a 26 times reduction from number of input samples to number of versions.

cs.CR↗

arXiv2017

Locally Differentially Private Heavy Hitter Identification

The notion of Local Differential Privacy (LDP) enables users to answer sensitive questions while preserving their privacy. The basic LDP frequent oracle protocol enables the aggregator to estimate the frequency of any value. But when the domain of input values is large, finding the most frequent values, also known as the heavy hitters, by estimating the frequencies of all possible values, is computationally infeasible. In this paper, we propose an LDP protocol for identifying heavy hitters. In our proposed protocol, which we call Prefix Extending Method (PEM), users are divided into groups, with each group reporting a prefix of her value. We analyze how to choose optimal parameters for the protocol and identify two design principles for designing LDP protocols with high utility. Experiments on both synthetic and real-world datasets demonstrate the advantage of our proposed protocol.

cs.CR↗

arXiv2017

Policy by Example: An Approach for Security Policy Specification

Policy specification for personal user data is a hard problem, as it depends on many factors that cannot be predetermined by system developers. Simultaneously, systems are increasingly relying on users to make security decisions. In this paper, we propose the approach of Policy by Example (PyBE) for specifying user-specific security policies. PyBE brings the benefits of the successful approach of programming by example (PBE) for program synthesis to the policy specification domain. In PyBE, users provide policy examples that specify if actions should be allowed or denied in certain scenarios. PyBE then predicts policy decisions for new scenarios. A key aspect of PyBE is its use of active learning to enable users to correct potential errors in their policy specification. To evaluate PyBE's effectiveness, we perform a feasibility study with expert users. Our study demonstrates that PyBE correctly predicts policies with 76% accuracy across all users, a significant improvement over naive approaches. Finally, we investigate the causes of inaccurate predictions to motivate directions for future research in this promising new domain.

cs.CR↗

arXiv2017

ROSA: R Optimizations with Static Analysis

R is a popular language and programming environment for data scientists. It is increasingly co-packaged with both relational and Hadoop-based data platforms and can often be the most dominant computational component in data analytics pipelines. Recent work has highlighted inefficiencies in executing R programs, both in terms of execution time and memory requirements, which in practice limit the size of data that can be analyzed by R. This paper presents ROSA, a static analysis framework to improve the performance and space efficiency of R programs. ROSA analyzes input programs to determine program properties such as reaching definitions, live variables, aliased variables, and types of variables. These inferred properties enable program transformations such as C++ code translation, strength reduction, vectorization, code motion, in addition to interpretive optimizations such as avoiding redundant object copies and performing in-place evaluations. An empirical evaluation shows substantial reductions by ROSA in execution time and memory consumption over both CRAN R and Microsoft R Open.

cs.PL↗

arXiv2017

Optimizing Locally Differentially Private Protocols

Protocols satisfying Local Differential Privacy (LDP) enable parties to collect aggregate information about a population while protecting each user's privacy, without relying on a trusted third party. LDP protocols (such as Google's RAPPOR) have been deployed in real-world scenarios. In these protocols, a user encodes his private information and perturbs the encoded value locally before sending it to an aggregator, who combines values that users contribute to infer statistics about the population. In this paper, we introduce a framework that generalizes several LDP protocols proposed in the literature. Our framework yields a simple and fast aggregation algorithm, whose accuracy can be precisely analyzed. Our in-depth analysis enables us to choose optimal parameters, resulting in two new protocols (i.e., Optimized Unary Encoding and Optimized Local Hashing) that provide better utility than protocols previously proposed. We present precise conditions for when each proposed protocol should be used, and perform experiments that demonstrate the advantage of our proposed protocols.

cs.CR↗

arXiv2017

Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics

While significant progress has been made separately on analytics systems for scalable stochastic gradient descent (SGD) and private SGD, none of the major scalable analytics frameworks have incorporated differentially private SGD. There are two inter-related issues for this disconnect between research and practice: (1) low model accuracy due to added noise to guarantee privacy, and (2) high development and runtime overhead of the private algorithms. This paper takes a first step to remedy this disconnect and proposes a private SGD algorithm to address \emph{both} issues in an integrated manner. In contrast to the white-box approach adopted by previous work, we revisit and use the classical technique of {\em output perturbation} to devise a novel "bolt-on" approach to private SGD. While our approach trivially addresses (2), it makes (1) even more challenging. We address this challenge by providing a novel analysis of the $L_2$-sensitivity of SGD, which allows, under the same privacy guarantees, better convergence of SGD when only a constant number of passes can be made over the data. We integrate our algorithm, as well as other state-of-the-art differentially private SGD, into Bismarck, a popular scalable SGD-based analytics system on top of an RDBMS. Extensive experiments show that our algorithm can be easily integrated, incurs virtually no overhead, scales well, and most importantly, yields substantially better (up to 4X) test accuracy than the state-of-the-art algorithms on many real datasets.

cs.LG↗

arXiv2017

Practical Black-Box Attacks against Machine Learning

Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to human observers. Potential attacks include having malicious content like malware identified as legitimate or controlling vehicle behavior. Yet, all existing adversarial example attacks require knowledge of either the model internals or its training data. We introduce the first practical demonstration of an attacker controlling a remotely hosted DNN with no such knowledge. Indeed, the only capability of our black-box adversary is to observe labels given by the DNN to chosen inputs. Our attack strategy consists in training a local model to substitute for the target DNN, using inputs synthetically generated by an adversary and labeled by the target DNN. We use the local substitute to craft adversarial examples, and find that they are misclassified by the targeted DNN. To perform a real-world and properly-blinded evaluation, we attack a DNN hosted by MetaMind, an online deep learning API. We find that their DNN misclassifies 84.24% of the adversarial examples crafted with our substitute. We demonstrate the general applicability of our strategy to many ML techniques by conducting the same attack against models hosted by Amazon and Google, using logistic regression substitutes. They yield adversarial examples misclassified by Amazon and Google at rates of 96.19% and 88.94%. We also find that this black-box attack strategy is capable of evading defense strategies previously found to make adversarial example crafting harder.

cs.CR↗

arXiv2016

Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks

Deep learning algorithms have been shown to perform extremely well on many classical machine learning problems. However, recent studies have shown that deep learning, like other machine learning techniques, is vulnerable to adversarial samples: inputs crafted to force a deep neural network (DNN) to provide adversary-selected outputs. Such attacks can seriously undermine the security of the system supported by the DNN, sometimes with devastating consequences. For example, autonomous vehicles can be crashed, illicit or illegal content can bypass content filters, or biometric authentication systems can be manipulated to allow improper access. In this work, we introduce a defensive mechanism called defensive distillation to reduce the effectiveness of adversarial samples on DNNs. We analytically investigate the generalizability and robustness properties granted by the use of defensive distillation when training DNNs. We also empirically study the effectiveness of our defense mechanisms on two DNNs placed in adversarial settings. The study shows that defensive distillation can reduce effectiveness of sample creation from 95% to less than 0.5% on a studied DNN. Such dramatic gains can be explained by the fact that distillation leads gradients used in adversarial sample creation to be reduced by a factor of 10^30. We also find that distillation increases the average minimum number of features that need to be modified to create adversarial samples by about 800% on one of the DNNs we tested.

cs.CR↗