arXiv research

It has been shown that adversaries can craft example inputs to neural networks which are similar to legitimate inputs but have been created to purposely cause the neural network to misclassify the input. These adversarial examples are crafted, for example, by calculating gradients of a carefully defined loss function w…

We inject undetectable backdoors into obfuscated neural networks and language models.

RENNs protect input privacy by rotating d-ary features.

This paper detects function-level obfuscation in binary code using graph-based methods.

In this work we revisit gradient regularization for adversarial robustness with some new ingredients. First, we derive new per-image theoretical robustness bounds based on local gradient information. These bounds strongly motivate input gradient regularization. Second, we implement a scaleable version of input gradient…

Adversarial training is an effective methodology for training deep neural networks that are robust against adversarial, norm-bounded perturbations. However, the computational cost of adversarial training grows prohibitively as the size of the model and number of input dimensions increase. Further, training against less…

The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural language data, inspired by homomorphic encryption. Our primary tool is {\em obfusc…

Identifying features that leak information about sensitive attributes is a key challenge in the design of information obfuscation mechanisms. In this paper, we propose a framework to identify information-leaking features via information density estimation. Here, features whose information densities exceed a pre-defined…

New flaw found in SAP defense, reducing its effectiveness to 0.1%.

This work presents Origami, which provides privacy-preserving inference for large deep neural network (DNN) models through a combination of enclave execution, cryptographic blinding, interspersed with accelerator-based computation. Origami partitions the ML model into multiple partitions. The first partition receives t…

We consider the problem of obfuscating sensitive information while preserving utility, and we propose a machine learning approach inspired by the generative adversarial networks paradigm. The idea is to set up two nets: the generator, that tries to produce an optimal obfuscation mechanism to protect the data, and the c…

This work enhances collaborative inference privacy by minimizing conditional entropy and boosting robustness against model inversion attacks.

Malware constitutes a major global risk affecting millions of users each year. Standard algorithms in detection systems perform insufficiently when dealing with malware passed through obfuscation tools. We illustrate this studying in detail an open source metamorphic software, making use of a hybrid framework to obtain…

Improves code2vec for Java classes by obfuscating variable names.

Deep neural networks require large amounts of resources which makes them hard to use on resource constrained devices such as Internet-of-things devices. Offloading the computations to the cloud can circumvent these constraints but introduces a privacy risk since the operator of the cloud is not necessarily trustworthy.…

The Android operating system has been the most popular for smartphones and tablets since 2012. This popularity has led to a rapid raise of Android malware in recent years. The sophistication of Android malware obfuscation and detection avoidance methods have significantly improved, making many traditional malware detec…

Executing deep neural networks for inference on the server-class or cloud backend based on data generated at the edge of Internet of Things is desirable due primarily to the limited compute power of edge devices and the need to protect the confidentiality of the inference neural networks. However, such a remote inferen…

Crowdsourced data used in machine learning services might carry sensitive information about attributes that users do not want to share. Various methods have been proposed to minimize the potential information leakage of sensitive attributes while maximizing the task accuracy. However, little is known about the theory b…

In this paper we investigate the usage of adversarial perturbations for the purpose of privacy from human perception and model (machine) based detection. We employ adversarial perturbations for obfuscating certain variables in raw data while preserving the rest. Current adversarial perturbation methods are used for dat…

Clustering algorithms have been increasingly adopted in security applications to spot dangerous or illicit activities. However, they have not been originally devised to deal with deliberate attack attempts that may aim to subvert the clustering process itself. Whether clustering can be safely adopted in such settings r…

Recurrent neural networks (RNNs) are powerful constructs capable of modeling complex systems, up to and including Turing Machines. However, learning such complex models from finite training sets can be difficult. In this paper we empirically show that RNNs can learn models of computer peripheral devices through input a…

The Internet of Things (IoT) will be a main data generation infrastructure for achieving better system intelligence. However, the extensive data collection and processing in IoT also engender various privacy concerns. This paper provides a taxonomy of the existing privacy-preserving machine learning approaches develope…

Text-based analysis methods allow to reveal privacy relevant author attributes such as gender, age and identify of the text's author. Such methods can compromise the privacy of an anonymous author even when the author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called Adver…

LLMs detect market patterns through causal reasoning, not just temporal association.

Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples--images with deliberately crafted, imperceptible noise to mislead the network's classification. To defend against adversarial examples, a plausible idea is to obfuscate the network's gradient with respect…

NKI integrates obfuscated datasets using nonlinear kernels for improved data collaboration.

We consider the problem of publicly releasing a dataset for support vector machine classification while not infringing on the privacy of data subjects (i.e., individuals whose private information is stored in the dataset). The dataset is systematically obfuscated using an additive noise for privacy protection. Motivate…

SONet stabilizes ODE networks for robustness without adversarial training.

Secure neural network inference on untrusted platforms using holographic reduced representations.

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'…

New defense method inspired by encryption improves visual classification accuracy.

We consider the problem of detecting malware with deep learning models, where the malware may be combined with significant amounts of benign code. Examples of this include piggybacking and trojan horse attacks on a system, where malicious behavior is hidden within a useful application. Such added flexibility in augment…

Paper defends sensitive attributes in GNNs from inference attacks.

Adversarial training is the most successful empirical method for increasing the robustness of neural networks against adversarial attacks. However, the most effective approaches, like training with Projected Gradient Descent (PGD) are accompanied by high computational complexity. In this paper, we present two ideas tha…

Paper proposes a method to encrypt faces while maintaining visual similarity.

A new method improves adversarial robustness and interpretability with reduced training time.

This work proposes a novel privacy-preserving method for synthetic replacement of sensitive data.

Digital image steganalysis, or the detection of image steganography, has been studied in depth for years and is driven by Advanced Persistent Threat (APT) groups', such as APT37 Reaper, utilization of steganographic techniques to transmit additional malware to perform further post-exploitation activity on a compromised…

Interpretability and fairness are critical in computer vision and machine learning applications, in particular when dealing with human outcomes, e.g. inviting or not inviting for a job interview based on application materials that may include photographs. One promising direction to achieve fairness is by learning data …

Simplifies fair PCA with fast, efficient solution.

The authors seek financial datasets to benchmark feature engineering methods on US market data.

Bayesian deep learning for graphs improves graph classification and prediction tasks.

With the celebrated success of deep learning, some attempts to develop effective methods for detecting malicious PowerShell programs employ neural nets in a traditional natural language processing setup while others employ convolutional neural nets to detect obfuscated malicious commands at a character level. While the…

Information systems have widely been the target of malware attacks. Traditional signature-based malicious program detection algorithms can only detect known malware and are prone to evasion techniques such as binary obfuscation, while behavior-based approaches highly rely on the malware training samples and incur prohi…

New mechanisms from primate vision improve neural network robustness.

Identifying meaningful signal buried in noise is a problem of interest arising in diverse scenarios of data-driven modeling. We present here a theoretical framework for exploiting intrinsic geometry in data that resists noise corruption, and might be identifiable under severe obfuscation. Our approach is based on uncov…

This paper improves privacy and fairness in federated learning by protecting sensitive data and ensuring group fairness.

New methods interpret clustering outcomes without altering data structure.