Related papers: Identifying Adversary Characteristics from an Obse…

Many machine learning adversarial attacks find adversarial samples of a victim model ${\mathcal M}$ by following the gradient of some attack objective functions, either explicitly or implicitly. To confuse and detect such attacks, we take…

Neural ranking models (NRMs) have undergone significant development and have become integral components of information retrieval (IR) systems. Unfortunately, recent research has unveiled the vulnerability of NRMs to adversarial document…

Recent studies have demonstrated that reinforcement learning (RL) agents are susceptible to adversarial manipulation, similar to vulnerabilities previously demonstrated in the supervised learning setting. While most existing work studies…

Due to their massive success in various domains, deep learning techniques are increasingly used to design network intrusion detection solutions that detect and mitigate unknown and known attacks with high accuracy detection rates and…

Many Machine Learning models are vulnerable to adversarial attacks: There exist methodologies that add a small (imperceptible) perturbation to an input such that the model comes up with a wrong prediction. Better understanding of such…

Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade…

Adversarial reprogramming allows stealing computational resources by repurposing machine learning models to perform a different task chosen by the attacker. For example, a model trained to recognize images of animals can be reprogrammed to…

Adversarial examples have proven to threaten speaker identification systems, and several countermeasures against them have been proposed. In this paper, we propose a method to detect the presence of adversarial examples, i.e., a binary…

Despite many proposed algorithms to provide robustness to deep learning (DL) models, DL models remain susceptible to adversarial attacks. We hypothesize that the adversarial vulnerability of DL models stems from two factors. The first…

In the past decades, the rise of artificial intelligence has given us the capabilities to solve the most challenging problems in our day-to-day lives, such as cancer prediction and autonomous navigation. However, these applications might…

Intrusion Detection Systems (IDS) enhanced with Machine Learning (ML) have demonstrated the capacity to efficiently build a prototype of "normal" cyber behaviors in order to detect cyber threats' activity with greater accuracy than…

In recent years, the topic of explainable machine learning (ML) has been extensively researched. Up until now, this research focused on regular ML users use-cases such as debugging a ML model. This paper takes a different posture and show…

Security of machine learning models is a concern as they may face adversarial attacks for unwarranted advantageous decisions. While research on the topic has mainly been focusing on the image domain, numerous industrial applications, in…

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…

Although deep neural networks have shown promising performances on various tasks, even achieving human-level performance on some, they are shown to be susceptible to incorrect predictions even with imperceptibly small perturbations to an…

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…

Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in mitigating one risk, it may correspond to increased or…

Machine learning algorithms can be fooled by small well-designed adversarial perturbations. This is reminiscent of cellular decision-making where ligands (called antagonists) prevent correct signalling, like in early immune recognition. We…

Susceptibility of neural networks to adversarial attack prompts serious safety concerns for lane detection efforts, a domain where such models have been widely applied. Recent work on adversarial road patches have successfully induced…

Open set domain adaptation refers to the scenario that the target domain contains categories that do not exist in the source domain. It is a more common situation in the reality compared with the typical closed set domain adaptation where…