Related papers: Evasion Attacks against Machine Learning at Test T…

Malware continues to be a major cyber threat, despite the tremendous effort that has been made to combat them. The number of malware in the wild steadily increases over time, meaning that we must resort to automated defense techniques. This…

The growing cybersecurity threats make it essential to use high-quality data to train Machine Learning (ML) models for network traffic analysis, without noisy or missing data. By selecting the most relevant features for cyber-attack…

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, there is a growing body…

Despite its success and popularity, machine learning is now recognized as vulnerable to evasion attacks, i.e., carefully crafted perturbations of test inputs designed to force prediction errors. In this paper we focus on evasion attacks…

Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these attacks, it has been proposed to limit the information provided to the adversary…

Advances in machine learning (ML) in recent years have enabled a dizzying array of applications such as data analytics, autonomous systems, and security diagnostics. ML is now pervasive---new systems and models are being deployed in every…

In the recent years, Portable Document Format, commonly known as PDF, has become a democratized standard for document exchange and dissemination. This trend has been due to its characteristics such as its flexibility and portability across…

Advances in machine learning have led to broad deployment of systems with impressive performance on important problems. Nonetheless, these systems can be induced to make errors on data that are surprisingly similar to examples the learned…

In the last years, Deep Learning technology has been proposed in different fields, bringing many advances in each of them, but identifying new threats in these solutions regarding cybersecurity. Those implemented models have brought several…

Machine Learning (ML) techniques can facilitate the automation of malicious software (malware for short) detection, but suffer from evasion attacks. Many studies counter such attacks in heuristic manners, lacking theoretical guarantees and…

Malware classifiers are subject to training-time exploitation due to the need to regularly retrain using samples collected from the wild. Recent work has demonstrated the feasibility of backdoor attacks against malware classifiers, and yet…

Intelligent machine learning approaches are finding active use for event detection and identification that allow real-time situational awareness. Yet, such machine learning algorithms have been shown to be susceptible to adversarial attacks…

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Artificial neural networks have been successfully used for many different classification tasks including malware detection and distinguishing between malicious and non-malicious programs. Although artificial neural networks perform very…

In recent years, deep learning has shown performance breakthroughs in many applications, such as image detection, image segmentation, pose estimation, and speech recognition. However, this comes with a major concern: deep networks have been…

Verifying the robustness of machine learning models against evasion attacks at test time is an important research problem. Unfortunately, prior work established that this problem is NP-hard for decision tree ensembles, hence bound to be…

Recently researchers have proposed using deep learning-based systems for malware detection. Unfortunately, all deep learning classification systems are vulnerable to adversarial attacks. Previous work has studied adversarial attacks against…

The openness of modern IT systems and their permanent change make it challenging to keep these systems secure. A combination of regression and security testing called security regression testing, which ensures that changes made to a system…

A large body of recent work has investigated the phenomenon of evasion attacks using adversarial examples for deep learning systems, where the addition of norm-bounded perturbations to the test inputs leads to incorrect output…