Related papers: Interdicting attack plans with boundedly-rational …
Adversarial attacks on explainability models have drastic consequences when explanations are used to understand the reasoning of neural networks in safety critical systems. Path methods are one such class of attribution methods susceptible…
There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against evasion or poisoning…
In this article I describe a research agenda for securing machine learning models against adversarial inputs at test time. This article does not present results but instead shares some of my thoughts about where I think that the field needs…
In this paper we demonstrate a new advance in causal Bayesian graphical modelling combined with Adversarial Risk Analysis. This research aims to support strategic analyses of various defensive interventions to counter the threat arising…
Deep reinforcement learning has shown promising results in learning control policies for complex sequential decision-making tasks. However, these neural network-based policies are known to be vulnerable to adversarial examples. This…
Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to adversarial examples. We find, however, that typical adaptive evaluations are incomplete. We demonstrate that thirteen defenses recently published at…
Operating in a dynamic real world environment requires a forward thinking and adversarial aware design for classifiers, beyond fitting the model to the training data. In such scenarios, it is necessary to make classifiers - a) harder to…
As AI-enabled cyber capabilities become more advanced, we propose "differential access" as a strategy to tilt the cybersecurity balance toward defense by shaping access to these capabilities. We introduce three possible approaches that form…
Learning models capable of providing reliable predictions in the face of adversarial actions has become a central focus of the machine learning community in recent years. This challenge arises from observing that data encountered at…
Deception plays a key role in adversarial or strategic interactions for the purpose of self-defence and survival. This paper introduces a general framework and solution to address deception. Most existing approaches for deception consider…
When used in automated decision-making systems, machine learning (ML) models are vulnerable to data-manipulation attacks. Some defense mechanisms (e.g., adversarial regularization) directly affect the ML models while others (e.g., anomaly…
As large language models grow increasingly capable, concerns about their safe deployment have intensified. While numerous alignment strategies aim to restrict harmful behavior, these defenses can still be circumvented through carefully…
Adversarial Training is proved to be an efficient method to defend against adversarial examples, being one of the few defenses that withstand strong attacks. However, traditional defense mechanisms assume a uniform attack over the examples…
The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…
We address the problem of allocating limited resources in a network under persistent yet statistically unknown adversarial attacks. Each node in the network may be degraded, but not fully disabled, depending on its available defensive…
For over a decade, cybersecurity has relied on human labor scarcity to limit attackers to high-value targets manually or generic automated attacks at scale. Building sophisticated exploits requires deep expertise and manual effort, leading…
A system relying on the collective behavior of decision-makers can be vulnerable to a variety of adversarial attacks. How well can a system operator protect performance in the face of these risks? We frame this question in the context of…
This study provides a new understanding of the adversarial attack problem by examining the correlation between adversarial attack and visual attention change. In particular, we observed that: (1) images with incomplete attention regions are…
In recent years machine learning algorithms, and more specifically deep learning algorithms, have been widely used in many fields, including cyber security. However, machine learning systems are vulnerable to adversarial attacks, and this…
Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems. In this work, we adopt a principled way and study…