no code implementations • 14 Mar 2024 • Shiqing Wei, Prashanth Krishnamurthy, Farshad Khorrami
Designing control inputs that satisfy safety requirements is crucial in safety-critical nonlinear control, and this task becomes particularly challenging when full-state measurements are unavailable.
1 code implementation • 26 Feb 2024 • Georg Pichler, Marco Romanelli, Divya Prakash Manivannan, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg
We introduce a formal statistical definition for the problem of backdoor detection in machine learning systems and use it to analyze the feasibility of such problems, providing evidence for the utility and applicability of our definition.
no code implementations • 25 Jan 2024 • Patricia Pauli, Aaron Havens, Alexandre Araujo, Siddharth Garg, Farshad Khorrami, Frank Allgöwer, Bin Hu
However, a direct application of LipSDP to the resultant residual ReLU networks is conservative and even fails in recovering the well-known fact that the MaxMin activation is 1-Lipschitz.
1 code implementation • 27 Oct 2023 • Sara Ghazanfari, Alexandre Araujo, Prashanth Krishnamurthy, Farshad Khorrami, Siddharth Garg
On the other hand, as perceptual metrics rely on neural networks, there is a growing concern regarding their resilience, given the established vulnerability of neural networks to adversarial attacks.
no code implementations • 21 Sep 2023 • Alireza Sarmadi, Prashanth Krishnamurthy, Farshad Khorrami
We show the efficacy of the algorithm in tuning the high-dimensional controller parameters and also reducing the number of evaluations required for the tuning.
1 code implementation • 27 Jul 2023 • Sara Ghazanfari, Siddharth Garg, Prashanth Krishnamurthy, Farshad Khorrami, Alexandre Araujo
In this paper, we propose the Robust Learned Perceptual Image Patch Similarity (R-LPIPS) metric, a new metric that leverages adversarially trained deep features.
no code implementations • 19 Jul 2023 • Vinicius Mariano Goncalves, Prashanth Krishnamurthy, Anthony Tzes, Farshad Khorrami
Control Barrier Functions and Quadratic Programming are increasingly used for designing controllers that consider critical safety constraints.
1 code implementation • 11 Jul 2023 • Hao Fu, Prashanth Krishnamurthy, Siddharth Garg, Farshad Khorrami
Having the computed five metrics, five novelty detectors are trained from the validation dataset.
no code implementations • 16 Jun 2023 • Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Marie-Pierre Revel, Siddharth Garg, Farshad Khorrami, Maria Vakalopoulou
The robustness of image segmentation has been an important research topic in the past few years as segmentation models have reached production-level accuracy.
no code implementations • 11 May 2023 • Bolun Dai, Prashanth Krishnamurthy, Andrew Papanicolaou, Farshad Khorrami
We develop a computationally efficient learning-based forward-backward stochastic differential equations (FBSDE) controller for both continuous and hybrid dynamical (HD) systems subject to stochastic noise and state constraints.
no code implementations • 16 Mar 2023 • Shiqing Wei, Prashanth Krishnamurthy, Farshad Khorrami
Based on a regularity condition on these uncertainties, we model them as bounded disturbances and prove that a CLF for the nominal system (estimate of the true system) is an input-to-state stable control Lyapunov function (ISS-CLF) for the true system when the CLF's gradient is bounded.
no code implementations • 15 Mar 2023 • Raktim Gautam Goswami, Prashanth Krishnamurthy, Farshad Khorrami
A methodology is developed to learn a feedback linearization (i. e., nonlinear change of coordinates and input transformation) using a data-driven approach for a single input control-affine nonlinear system with unknown dynamics.
no code implementations • 10 Mar 2023 • Bolun Dai, Heming Huang, Prashanth Krishnamurthy, Farshad Khorrami
Then, a probability distribution based on the priority score of the data points is used to sample data and update the learned CBF.
no code implementations • 25 Jan 2023 • Andrew Papanicolaou, Hao Fu, Prashanth Krishnamurthy, Farshad Khorrami
When $\epsilon$ is small, we can implement an NN algorithm based on the expansion of the solution in powers of $\epsilon$.
no code implementations • 16 Dec 2022 • Hao Fu, Prashanth Krishnamurthy, Siddharth Garg, Farshad Khorrami
In domain shift analysis, we propose a theorem based on our bound.
no code implementations • 13 Dec 2022 • Alireza Sarmadi, Hao Fu, Prashanth Krishnamurthy, Siddharth Garg, Farshad Khorrami
As a baseline, in Cooperatively Trained Feature Extractor (CTFE) Learning, the entities train models by sharing raw data.
no code implementations • 11 May 2022 • Bolun Dai, Prashanth Krishnamurthy, Farshad Khorrami
With our proposed approach, we can generate safe controllers that are less conservative and computationally more efficient.
no code implementations • 2 Feb 2022 • Hammond Pearce, Benjamin Tan, Prashanth Krishnamurthy, Farshad Khorrami, Ramesh Karri, Brendan Dolan-Gavitt
Large language models (such as OpenAI's Codex) have demonstrated impressive zero-shot multi-task capabilities in the software domain, including code explanation.
no code implementations • 5 Apr 2021 • Bolun Dai, Prashanth Krishnamurthy, Andrew Papanicolaou, Farshad Khorrami
In this paper, we propose a new methodology for state constrained stochastic optimal control (SOC) problems.
no code implementations • 8 Nov 2020 • Naman Patel, Prashanth Krishnamurthy, Siddharth Garg, Farshad Khorrami
We show that by controlling parts of a physical environment in which a pre-trained deep neural network (DNN) is being fine-tuned online, an adversary can launch subtle data poisoning attacks that degrade the performance of the system.
no code implementations • 4 Nov 2020 • Hao Fu, Akshaj Kumar Veldanda, Prashanth Krishnamurthy, Siddharth Garg, Farshad Khorrami
This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers.
no code implementations • 6 Apr 2020 • Virinchi Roy Surabhi, Prashanth Krishnamurthy, Hussam Amrouch, Kanad Basu, Jörg Henkel, Ramesh Karri, Farshad Khorrami
Combining IC aging with over-clocking produces a pattern of bit errors at the IC output by the induced timing violations.
1 code implementation • 19 Feb 2020 • Akshaj Kumar Veldanda, Kang Liu, Benjamin Tan, Prashanth Krishnamurthy, Farshad Khorrami, Ramesh Karri, Brendan Dolan-Gavitt, Siddharth Garg
This paper proposes a novel two-stage defense (NNoculation) against backdoored neural networks (BadNets) that, repairs a BadNet both pre-deployment and online in response to backdoored test inputs encountered in the field.
no code implementations • 12 Nov 2018 • Naman Patel, Apoorva Nandini Saridena, Anna Choromanska, Prashanth Krishnamurthy, Farshad Khorrami
The paper proposes an on-line monitoring framework for continuous real-time safety/security in learning-based control systems (specifically application to a unmanned ground vehicle).