no code implementations • 29 Aug 2022 • Anshuka Rangi, Haifeng Xu, Long Tran-Thanh, Massimo Franceschetti
To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate \emph{any} order-optimal learning algorithm towards a targeted policy in episodic RL and examines the potential damage of two natural types of poisoning attacks, i. e., the manipulation of \emph{reward} and \emph{action}.
no code implementations • 15 Feb 2021 • Anshuka Rangi, Long Tran-Thanh, Haifeng Xu, Massimo Franceschetti
In particular, for the case of unlimited verifications, we show that with $O(\log T)$ expected number of verifications, a simple modified version of the ETC type bandit algorithm can restore the order optimal $O(\log T)$ regret irrespective of the amount of contamination used by the attacker.
no code implementations • 5 Jan 2021 • Anshuka Rangi, Massimo Franceschetti, Long Tran-Thanh
We then propose bandit algorithms for the two feedback models and show that upper and lower bounds on the regret are of the order of $\tilde{O}(N^{2/3})$ and $\tilde\Omega(N^{2/3})$, respectively, where $N$ is the total number of users.
1 code implementation • 29 Dec 2020 • Vikas Dhiman, Mohammad Javad Khojasteh, Massimo Franceschetti, Nikolay Atanasov
This paper focuses on learning a model of system dynamics online while satisfying safety constraints.
no code implementations • 21 Nov 2020 • Anshuka Rangi, Mohammad Javad Khojasteh, Massimo Franceschetti
We study the trade-offs between the information acquired by the attacker from observations, the detection capabilities of the controller, and the control cost.
1 code implementation • L4DC 2020 • Mohammad Javad Khojasteh, Vikas Dhiman, Massimo Franceschetti, Nikolay Atanasov
This paper focuses on learning a model of system dynamics online while satisfying safety constraints. Our motivation is to avoid offline system identification or hand-specified dynamics models and allowa system to safely and autonomously estimate and adapt its own model during online operation. Given streaming observations of the system state, we use Bayesian learning to obtain a distributionover the system dynamics.
1 code implementation • 10 Jun 2019 • Hamed Omidvar, Vahideh Akhlaghi, Massimo Franceschetti, Rajesh K. Gupta
We introduce a simple auxiliary neural network which can generate the convolutional filters of any CNN architecture from a low dimensional latent space.
no code implementations • 24 Oct 2018 • Hamed Omidvar, Massimo Franceschetti
Finally, we show that when particles are placed on the infinite lattice $\mathbb{Z}^2$ rather than on a flat torus, for the values of $\tau$ mentioned above, sufficiently large $N$, and after a sufficiently long evolution time, any particle is contained in a large monochromatic region of size exponential in $N$, almost surely.
Social and Information Networks Mathematical Physics Mathematical Physics
no code implementations • 23 Oct 2018 • Anshuka Rangi, Massimo Franceschetti
For the two special cases of symmetric PI setting and MAB, the expected regret of both of these algorithms is order optimal in the duration of the learning process.
no code implementations • 17 Sep 2018 • Mohammad Javad Khojasteh, Anatoly Khina, Massimo Franceschetti, Tara Javidi
In the case of scalar plants, we derive an upper bound on the attacker's deception probability for any measurable control policy when the attacker uses an arbitrary learning algorithm to estimate the system dynamics.
no code implementations • 12 Sep 2018 • Anshuka Rangi, Massimo Franceschetti, Stefano Marano
In the first case, the network nodes interact with each other through a central entity, which plays the role of a fusion center.
no code implementations • 1 Apr 2018 • Mohammad Javad Khojasteh, Massimo Franceschetti, Gireeja Ranade
Each symbol transmitted from a sensor to a controller in a closed-loop system is received subject to some to random delay.
no code implementations • 1 Apr 2018 • Hamed Omidvar, Massimo Franceschetti
When particles are placed on the infinite lattice $\mathbb{Z}^2$ rather than on a flat torus, for the values of $\tau$ mentioned above, sufficiently large $N$, and after a sufficiently long evolution time, any particle is contained in a large monochromatic region of size exponential in $N$, almost surely.
Probability Distributed, Parallel, and Cluster Computing Social and Information Networks Mathematical Physics Mathematical Physics