Related papers: Towards Realistic Threat Modeling: Attack Commodif…

The recent growth in data availability in football has increased the risk of incorrect use of data-driven models, making guidelines on their validation and application necessary. The Expected Threat (xT) model is an accessible option for…

Model explanations provide transparency into a trained machine learning model's blackbox behavior to a model builder. They indicate the influence of different input attributes to its corresponding model prediction. The dependency of…

Despite the surging development and utilization of IoT devices, the security of IoT devices is still in infancy. The security pitfalls of IoT devices have made it easy for hackers to take over IoT devices and use them for malicious…

Traditional security analyses are often geared towards cryptographic primitives or protocols. Although such analyses are necessary, they cannot address a defender's need for insight into {\em which aspects of a networked system having a…

Graph modeling allows numerous security problems to be tackled in a general way, however, little work has been done to understand their ability to withstand adversarial attacks. We design and evaluate two novel graph attacks against a…

Benefiting from the rapid development of deep learning, 2D and 3D computer vision applications are deployed in many safe-critical systems, such as autopilot and identity authentication. However, deep learning models are not trustworthy…

This paper discusses the problem of estimating the state of a linear time-invariant system when some of its sensors and actuators are compromised by an adversarial agent. In the model considered in this paper, the malicious agent attacks an…

The continued integration of technology into all aspects of society stresses the need to identify and understand the risk associated with assimilating new technologies. This necessity is heightened when technology is used for medical…

Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…

Language models are prone to memorizing their training data, making them vulnerable to extraction attacks. While existing research often examines isolated setups, such as a single model or a fixed prompt, real-world adversaries have a…

An outstanding challenge with safety methods for human-robot interaction is reducing their conservatism while maintaining robustness to variations in human behavior. In this work, we propose that robots use confidence-aware game-theoretic…

Today, there is a plethora of software security tools employing visualizations that enable the creation of useful and effective interactive security analyst dashboards. Such dashboards can assist the analyst to understand the data at hand…

Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service API. In providing an in-depth characterization of…

Numerous safety- or security-critical systems depend on cameras to perceive their surroundings, further allowing artificial intelligence (AI) to analyze the captured images to make important decisions. However, a concerning attack vector…

Active cyber defenses based on temporal platform diversity have been proposed as way to make systems more resistant to attacks. These defenses change the properties of the platforms in order to make attacks more complicated. Unfortunately,…

Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this…

Probabilistic Graphical Bayesian models of causation have continued to impact on strategic analyses designed to help evaluate the efficacy of different interventions on systems. However, the standard causal algebras upon which these…

In this work, we highlight and perform a comprehensive study on calibration attacks, a form of adversarial attacks that aim to trap victim models to be heavily miscalibrated without altering their predicted labels, hence endangering the…

Attack graphs are a tool for analyzing security vulnerabilities that capture different and prospective attacks on a system. As a threat modeling tool, it shows possible paths that an attacker can exploit to achieve a particular goal.…

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…