English
Related papers

Related papers: How Sensor Attacks Transfer Across Lie Groups

200 papers

Adversarial attacks can mislead deep neural networks (DNNs) by adding imperceptible perturbations to benign examples. The attack transferability enables adversarial examples to attack black-box DNNs with unknown architectures or parameters,…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Kaisheng Liang , Bin Xiao

We present several theoretical contributions which allow Lie groups to be fit to high dimensional datasets. Transformation operators are represented in their eigen-basis, reducing the computational complexity of parameter estimation to that…

Computer Vision and Pattern Recognition · Computer Science 2017-06-08 Jascha Sohl-Dickstein , Ching Ming Wang , Bruno A. Olshausen

The problem of mitigating maliciously injected signals in interconnected systems is dealt with in this paper. We consider the class of covert attacks, as they are stealthy and cannot be detected by conventional means in centralized…

Systems and Control · Electrical Eng. & Systems 2021-04-15 Angelo Barboni , Thomas Parisini

While true phase transitions are forbidden in one-dimensional systems with short-range interactions, several models have recently been shown to exhibit sharp yet analytic thermodynamic anomalies that mimic thermal phase transitions. We show…

Statistical Mechanics · Physics 2026-01-21 Onofre Rojas

We study the problem of collaboratively estimating the state of an LTI system monitored by a network of sensors, subject to the following important practical considerations: (i) certain sensors might be arbitrarily compromised by an…

Systems and Control · Computer Science 2018-01-29 Aritra Mitra , Shreyas Sundaram

As machine learning models become increasingly deployed across the edge of internet of things environments, a partitioned deep learning paradigm in which models are split across multiple computational nodes introduces a new dimension of…

Machine Learning · Computer Science 2025-07-11 Giulio Rossolini , Fabio Brau , Alessandro Biondi , Battista Biggio , Giorgio Buttazzo

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We…

Cryptography and Security · Computer Science 2018-11-02 Luca Melis , Congzheng Song , Emiliano De Cristofaro , Vitaly Shmatikov

Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside. In this work, we demonstrate that there can exist a downside after all: bias…

Machine Learning · Computer Science 2022-07-07 Hadi Salman , Saachi Jain , Andrew Ilyas , Logan Engstrom , Eric Wong , Aleksander Madry

Many security protocols rely on the assumptions on the physical properties in which its protocol sessions will be carried out. For instance, Distance Bounding Protocols take into account the round trip time of messages and the transmission…

Logic in Computer Science · Computer Science 2017-10-05 Max Kanovich , Tajana Ban Kirigin , Vivek Nigam , Andre Scedrov , Carolyn Talcott

Though deep neural networks perform challenging tasks excellently, they are susceptible to adversarial examples, which mislead classifiers by applying human-imperceptible perturbations on clean inputs. Under the query-free black-box…

Machine Learning · Computer Science 2020-11-05 Zifei Zhang , Kai Qiao , Jian Chen , Ningning Liang

We prove that steady state bifurcations in finite-dimensional dynamical systems that are symmetric with respect to a monoid representation generically occur along an absolutely indecomposable subrepresentation. This is stated as a…

Dynamical Systems · Mathematics 2018-10-10 Sören Schwenker

Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, it still leaves a long way to go for generating transferable…

Computer Vision and Pattern Recognition · Computer Science 2022-01-04 Yexin Duan , Junhua Zou , Xingyu Zhou , Wu Zhang , Jin Zhang , Zhisong Pan

In this work, we focus on analyzing vulnerability of nonlinear dynamical control systems to stealthy false data injection attacks on sensors. We start by defining the stealthiness notion in the most general form where an attack is…

Systems and Control · Electrical Eng. & Systems 2023-10-10 Amir Khazraei , Miroslav Pajic

We investigate quantum state transfer on a class of bipartite graphs, namely the butterfly graphs, within the framework of discrete-time quantum walks. These graphs facilitate the construction of scalable quantum networks that enable…

Quantum Physics · Physics 2026-04-14 Monika Rani , Subhashish Banerjee , Nikhil Swami , Supriyo Dutta

Symmetry breaking--the phenomenon in which the symmetry of a system is not inherited by its stable states--underlies pattern formation, superconductivity, and numerous other effects. Recent theoretical work has established the possibility…

Adaptation and Self-Organizing Systems · Physics 2021-09-24 Ferenc Molnar , Takashi Nishikawa , Adilson E. Motter

In this paper, we investigate data-driven attack detection and identification in a model-free setting. We consider a practically motivated scenario in which the available dataset may be compromised by malicious sensor attacks, but contains…

Systems and Control · Electrical Eng. & Systems 2026-02-09 Takumi Shinohara , Karl H. Johansson , Henrik Sandberg

We study the performance of perception-based control systems in the presence of attacks, and provide methods for modeling and analysis of their resiliency to stealthy attacks on both physical and perception-based sensing. Specifically, we…

Systems and Control · Electrical Eng. & Systems 2023-08-29 Amir Khazraei , Henry Pfister , Miroslav Pajic

In recent years, deep learning (DL) models have achieved significant progress in many domains, such as autonomous driving, facial recognition, and speech recognition. However, the vulnerability of deep learning models to adversarial attacks…

Cryptography and Security · Computer Science 2023-04-19 Feng Guo , Zheng Sun , Yuxuan Chen , Lei Ju

Machine Learning (ML) and Deep Learning (DL) models have achieved state-of-the-art performance on multiple learning tasks, from vision to natural language modelling. With the growing adoption of ML and DL to many areas of computer science,…

Machine Learning · Computer Science 2019-06-11 Anshuman Chhabra , Abhishek Roy , Prasant Mohapatra

In recent years, a number of process-based anomaly detection schemes for Industrial Control Systems were proposed. In this work, we provide the first systematic analysis of such schemes, and introduce a taxonomy of properties that are…

Cryptography and Security · Computer Science 2023-06-27 Alessandro Erba , Nils Ole Tippenhauer
‹ Prev 1 3 4 5 6 7 10 Next ›