Related papers: How Sensor Attacks Transfer Across Lie Groups

Data forging attacks provide counterfactual proof that a model was trained on a given dataset, when in fact, it was trained on another. These attacks work by forging (replacing) mini-batches with ones containing distinct training examples…

This paper considers the state reconstruction problem for discrete-time cyber-physical systems when some of the sensors can be arbitrarily corrupted by malicious attacks where the attacked sensors belong to an unknown set. We first prove…

Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks…

This paper focuses on the problem of cyber attacks for discrete event systems under supervisory control. In more detail, the goal of the supervisor, who has a partial observation of the system evolution, is that of preventing the system…

State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}:…

Transfer learning is prevalent as a technique to efficiently generate new models (Student models) based on the knowledge transferred from a pre-trained model (Teacher model). However, Teacher models are often publicly available for sharing…

We describe defense mechanisms designed to detect sophisticated grid attacks involving both physical actions (including load modification) and sensor output alteration, with the latter performed in a sparse manner and also so as to take…

What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this work, we investigate this question in the setting of high-dimensional binary classification, where…

Attacks, including the manipulation of sensor readings and the modification of actuator commands, pose a significant challenge to the security and privacy of automated systems. This paper considers discrete event systems that can be modeled…

Adversarial examples have posed a severe threat to deep neural networks due to their transferable nature. Currently, various works have paid great efforts to enhance the cross-model transferability, which mostly assume the substitute model…

Transferability-based adversarial attacks exploit the ability of adversarial examples, crafted to deceive a specific source Intrusion Detection System (IDS) model, to also mislead a target IDS model without requiring access to the training…

We consider the dynamics of strongly localized systems subject to dephasing noise with arbitrary correlation time. Although noise inevitably induces delocalization, transport in the noise-induced delocalized phase is subdiffusive in a…

Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of full-scale data, offering substantial gains in efficiency. Recent studies reveal that the condensation process can be vulnerable…

In the problem of location anonymity of the events exposed to a global eavesdropper, we highlight and analyze some aspects that are missing in the prior work, which is especially relevant for the quality of secure sensing in…

A common assumption in the social learning literature is that agents exchange information in an unselfish manner. In this work, we consider the scenario where a subset of agents aims at deceiving the network, meaning they aim at driving the…

Semantic communication enhances transmission efficiency by conveying semantic information rather than raw input symbol sequences. Task-oriented semantic communication is a variant that tries to retains only task-specific information, thus…

The prominent success of neural networks, mainly in computer vision tasks, is increasingly shadowed by their sensitivity to small, barely perceivable adversarial perturbations in image input. In this work, we aim at explaining this…

As more attention is paid to security in the context of control systems and as attacks occur to real control systems throughout the world, it has become clear that some of the most nefarious attacks are those that evade detection. The term…

Clustering algorithms are used in a large number of applications and play an important role in modern machine learning-- yet, adversarial attacks on clustering algorithms seem to be broadly overlooked unlike supervised learning. In this…

A common approach to overcome the limited nature of sensor networks is to aggregate data at intermediate nodes. A challenging issue in this context is to guarantee end-to-end security mainly because sensor networks are extremely vulnerable…