Related papers: Et Tu Certifications: Robustness Certificates Yiel…
Recent works show that Graph Neural Networks (GNNs) are highly non-robust with respect to adversarial attacks on both the graph structure and the node attributes, making their outcomes unreliable. We propose the first method for certifiable…
While machine learning models have proven effective across various scenarios, it is widely acknowledged that many models are vulnerable to adversarial attacks. Recently, there have emerged numerous efforts in adversarial defense. Among…
High sensitivity of neural networks against malicious perturbations on inputs causes security concerns. To take a steady step towards robust classifiers, we aim to create neural network models provably defended from perturbations. Prior…
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…
Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…
While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being…
It has been empirically observed that defense mechanisms designed to protect neural networks against $\ell_\infty$ adversarial examples offer poor performance against $\ell_2$ adversarial examples and vice versa. In this paper we conduct a…
Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples…
The phenomenon of Adversarial Examples is attracting increasing interest from the Machine Learning community, due to its significant impact to the security of Machine Learning systems. Adversarial examples are similar (from a perceptual…
Neural networks are vulnerable to backdoor poisoning attacks, where the attackers maliciously poison the training set and insert triggers into the test input to change the prediction of the victim model. Existing defenses for backdoor…
Patch robustness certification is an emerging kind of defense technique against adversarial patch attacks with provable guarantees. There are two research lines: certified recovery and certified detection. They aim to label malicious…
The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an…
The existence of adversarial examples has led to considerable uncertainty regarding the trust one can justifiably put in predictions produced by automated systems. This uncertainty has, in turn, lead to considerable research effort in…
Deep learning-based malware detection systems are vulnerable to adversarial EXEmples - carefully-crafted malicious programs that evade detection with minimal perturbation. As such, the community is dedicating effort to develop mechanisms to…
Model attribution is a popular tool to explain the rationales behind model predictions. However, recent work suggests that the attributions are vulnerable to minute perturbations, which can be added to input samples to fool the attributions…
This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. We suggest creating a neighborhood around each training…
Adversarial robustness refers to a model's ability to resist perturbation of inputs, while distribution robustness evaluates the performance of the model under data shifts. Although both aim to ensure reliable performance, prior work has…
In malware behavioral analysis, the list of accessed and created files very often indicates whether the examined file is malicious or benign. However, malware authors are trying to avoid detection by generating random filenames and/or…
The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerability from a data perspective by showing that one can extract…
On the one hand, there has been considerable progress on neural network verification in recent years, which makes certifying neural networks a possibility. On the other hand, neural networks in practice are often re-trained over time to…