Related papers: On the existence of consistent adversarial attacks…

Despite the great success achieved in machine learning (ML), adversarial examples have caused concerns with regards to its trustworthiness: A small perturbation of an input results in an arbitrary failure of an otherwise seemingly…

With the recent advancements in machine learning (ML), numerous ML-based approaches have been extensively applied in software analytics tasks to streamline software development and maintenance processes. Nevertheless, studies indicate that…

State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…

This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate 'adversarial risk' as an objective for achieving models robust to worst-case inputs. We then…

Deep neural networks are easily misled by adversarial examples. Although lots of defense methods are proposed, many of them are demonstrated to lose effectiveness when against properly performed adaptive attacks. How to evaluate the…

We identify three common cases that lead to overestimation of adversarial accuracy against bounded first-order attack methods, which is popularly used as a proxy for adversarial robustness in empirical studies. For each case, we propose…

Machine learning methods in general and Deep Neural Networks in particular have shown to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been studied in the context of whole-image classification. In this…

Robustness of machine learning models is critical for security related applications, where real-world adversaries are uniquely focused on evading neural network based detectors. Prior work mainly focus on crafting adversarial examples (AEs)…

Deep Neural Networks (DNNs) have been widely applied in various recognition tasks. However, recently DNNs have been shown to be vulnerable against adversarial examples, which can mislead DNNs to make arbitrary incorrect predictions. While…

In recent years Deep Neural Networks (DNNs) have achieved remarkable results and even showed super-human capabilities in a broad range of domains. This led people to trust in DNNs' classifications and resulting actions even in…

Machine learning models are vulnerable to adversarial examples formed by applying small carefully chosen perturbations to inputs that cause unexpected classification errors. In this paper, we perform experiments on various adversarial…

Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high "standard" accuracy to produce an incorrect prediction with high…

Malware is constantly adapting in order to avoid detection. Model based malware detectors, such as SVM and neural networks, are vulnerable to so-called adversarial examples which are modest changes to detectable malware that allows the…

Despite numerous attempts to defend deep learning based image classifiers, they remain susceptible to the adversarial attacks. This paper proposes a technique to identify susceptible classes, those classes that are more easily subverted. To…

Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phenomenon about the…

Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…

The ability to transfer adversarial attacks from one model (the surrogate) to another model (the victim) has been an issue of concern within the machine learning (ML) community. The ability to successfully evade unseen models represents an…

Pre-trained models excel on NLI benchmarks like SNLI and MultiNLI, but their true language understanding remains uncertain. Models trained only on hypotheses and labels achieve high accuracy, indicating reliance on dataset biases and…

Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety of real-world machine learning applications because…

Current reading comprehension models generalise well to in-distribution test sets, yet perform poorly on adversarially selected inputs. Most prior work on adversarial inputs studies oversensitivity: semantically invariant text perturbations…