arXiv research

ATHENA builds flexible defenses against adversarial attacks.

A Bayesian framework models adversarial uncertainty for robust machine learning.

The paper evaluates machine learning cyber defenses using log data against adversarial attacks.

Unified framework for analyzing model stealing attacks and defenses.

This paper proposes a framework for certifying neural network defenses against data poisoning attacks.

Image classifiers often suffer from adversarial examples, which are generated by strategically adding a small amount of noise to input images to trick classifiers into misclassification. Over the years, many defense mechanisms have been proposed, and different researchers have made seemingly contradictory claims on the…

Paper analyzes adversarial attacks and defenses using game theory.

Feature Squeezing is a recently proposed defense method which reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample. It has been shown that feature squeezing defenses can be combined in a joint detection fram…

Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN model to misclassify. In this paper, we present a cross-layer strategic ensemble fra…

Despite being popularly used in many applications, neural network models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose potential risks on safety and security critical applications. However, existing def…

DAD++ improves test-time adversarial defense without access to training data.

Automates perturbation analysis for neural networks, enabling certified robustness on complex architectures.

In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can cause misclassification of legitimate images. We propose Defense-GAN, a new fra…

We improve image perturbation defenses using a better-defined Wasserstein threat model.

InvGAN solves GAN inference problem without training data.

Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities …

PatchGuard defends against localized adversarial patches with provable robustness.

This paper studies backdoor attacks in federated learning and proposes defenses.

Machine learning (ML) classifiers are vulnerable to adversarial examples. An adversarial example is an input sample which is slightly modified to induce misclassification in an ML classifier. In this work, we investigate white-box and grey-box evasion attacks to an ML-based malware detector and conduct performance eval…

In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the Normal- Hedge bound, which mainly depends on the effective number of experts but also weakly depends on the nominal…

New defense method inspired by encryption improves visual classification accuracy.

TensorShield defends images from adversarial attacks using tensor decomposition.

Automated discovery of adaptive attacks improves adversarial defense evaluation.

New research shows many recent defenses against adversarial examples are ineffective against black-box attacks.

Backdoor attacks are possible in feature-partitioned collaborative learning, even without labels.

Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs…

Enhances deep learning models' robustness against adversarial attacks.

Paper presents certified defenses against adversarial patch attacks.

New adaptive attacks bypass many defenses to adversarial examples.

This study evaluates adversarial attacks and defenses for chest X-ray disease classification.

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 var…

Stochastic defense improves natural classifiers against adversarial attacks.

Defense against small image patches using occlusions.

Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs, can mislead a DNN to classify them as any target labels. This work provides a solution to hardening DNNs under adversarial attacks through…

Defense against ASR attacks using dropout uncertainty.

Survey of algorithms to correct past mistakes in prediction.

We provide recovery guarantees for compressible signals that have been corrupted with noise and extend the framework introduced in \cite{bafna2018thwarting} to defend neural networks against $\ell_0$-norm, $\ell_2$-norm, and $\ell_{\infty}$-norm attacks. Our results are general as they can be applied to most unitary tr…

We propose a novel defense against all existing gradient based adversarial attacks on deep neural networks for image classification problems. Our defense is based on a combination of deep neural networks and simple image transformations. While straightforward in implementation, this defense yields a unique security pro…

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 …

High-performance Deep Neural Networks (DNNs) are increasingly deployed in many real-world applications e.g., cloud prediction APIs. Recent advances in model functionality stealing attacks via black-box access (i.e., inputs in, predictions out) threaten the business model of such applications, which require a lot of tim…

In this appraisal paper, we evaluate the efficacy of SHIELD, a compression-based defense framework for countering adversarial attacks on image classification models, which was published at KDD 2018. Here, we consider alternative threat models not studied in the original work, where we assume that an adaptive adversary …

This paper benchmarks time-series adversarial defenses and attacks.

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 understan…

Correctly evaluating defenses against adversarial examples has proven to be extremely difficult. Despite the significant amount of recent work attempting to design defenses that withstand adaptive attacks, few have succeeded; most papers that propose defenses are quickly shown to be incorrect. We believe a large contri…

DeepRobust is a PyTorch library for adversarial attacks and defenses.

New defense method reduces adversarial attacks on neural networks.

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; w…

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…