Related papers: Query complexity of adversarial attacks
Recent advances in attention-based networks have shown that Vision Transformers can achieve state-of-the-art or near state-of-the-art results on many image classification tasks. This puts transformers in the unique position of being a…
While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable. This frailness takes the form of small, carefully chosen perturbations of their input,…
Adversarial attacks are widely used to identify model vulnerabilities; however, their validity as proxies for robustness to random perturbations remains debated. We ask whether an adversarial example provides a representative estimate of…
Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…
Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…
Adversarial examples are important for understanding the behavior of neural models, and can improve their robustness through adversarial training. Recent work in natural language processing generated adversarial examples by assuming…
We analyze the number of queries that a whitebox adversary needs to make to a private learner in order to reconstruct its training data. For $(\epsilon, \delta)$ DP learners with training data drawn from any arbitrary compact metric space,…
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…
Adversarial examples, which are slightly perturbed inputs generated with the aim of fooling a neural network, are known to transfer between models; adversaries which are effective on one model will often fool another. This concept of…
Despite the impressive performances reported by deep neural networks in different application domains, they remain largely vulnerable to adversarial examples, i.e., input samples that are carefully perturbed to cause misclassification at…
In the thesis, we use a recently developed tight characterisation of quantum query complexity, the adversary bound, to develop new quantum algorithms and lower bounds. Our results are as follows: * We develop a new technique for the…
We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers. We demonstrate how this problem can be framed as finding strategies at equilibrium in a two-player,…
Machine learning models using transaction records as inputs are popular among financial institutions. The most efficient models use deep-learning architectures similar to those in the NLP community, posing a challenge due to their…
We revisit the concept of "adversary" in online learning, motivated by solving robust optimization and adversarial training using online learning methods. While one of the classical setups in online learning deals with the "adversarial"…
Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers. However, in the black-box setting, the attacker is limited only to the query…
Deep neural networks learn fragile "shortcut" features, rendering them difficult to interpret (black box) and vulnerable to adversarial attacks. This paper proposes semantic features as a general architectural solution to this problem. The…
Adversarial attacks against deep learning models have gained significant attention and recent works have proposed explanations for the existence of adversarial examples and techniques to defend the models against these attacks. Attention in…
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In previous studies, the use of models encrypted with a secret key was demonstrated to be robust against white-box attacks, but not against black-box…
While adversarial robustness in computer vision is a mature research field, fewer researchers have tackled the evasion attacks against tabular deep learning, and even fewer investigated robustification mechanisms and reliable defenses. We…
Adversarial attacks have been extensively studied in recent years since they can identify the vulnerability of deep learning models before deployed. In this paper, we consider the black-box adversarial setting, where the adversary needs to…