Search Results for author:
Found 24 papers, 5 papers with code
Confidence-Aware Safe and Stable Control of Control-Affine Systems
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.
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
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.
Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations
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.
LipSim: A Provably Robust Perceptual Similarity Metric
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.
High-Dimensional Controller Tuning through Latent Representations
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.
R-LPIPS: An Adversarially Robust Perceptual Similarity Metric
In this paper, we propose the Robust Learned Perceptual Image Patch Similarity (R-LPIPS) metric, a new metric that leverages adversarially trained deep features.
Using Circulation to Mitigate Spurious Equilibria in Control Barrier Function -- Extended Version
Control Barrier Functions and Quadratic Programming are increasingly used for designing controllers that consider critical safety constraints.
Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detection
Having the computed five metrics, five novelty detectors are trained from the validation dataset.
Towards Better Certified Segmentation via Diffusion Models
The robustness of image segmentation has been an important research topic in the past few years as segmentation models have reached production-level accuracy.
State Constrained Stochastic Optimal Control for Continuous and Hybrid Dynamical Systems Using DFBSDE
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.
Neural Lyapunov Control for Nonlinear Systems with Unstructured Uncertainties
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.
Data-Driven Deep Learning Based Feedback Linearization of Systems with Unknown Dynamics
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.
Data-Efficient Control Barrier Function Refinement
Then, a probability distribution based on the priority score of the data points is used to sample data and update the learned CBF.
A Deep Neural Network Algorithm for Linear-Quadratic Portfolio Optimization with MGARCH and Small Transaction Costs
When $\epsilon$ is small, we can implement an NN algorithm based on the expansion of the solution in powers of $\epsilon$.
An Upper Bound for the Distribution Overlap Index and Its Applications
In domain shift analysis, we propose a theorem based on our bound.
Privacy-Preserving Collaborative Learning through Feature Extraction
As a baseline, in Cooperatively Trained Feature Extractor (CTFE) Learning, the entities train models by sharing raw data.
Learning a Better Control Barrier Function
With our proposed approach, we can generate safe controllers that are less conservative and computationally more efficient.
Pop Quiz! Can a Large Language Model Help With Reverse Engineering?
Large language models (such as OpenAI's Codex) have demonstrated impressive zero-shot multi-task capabilities in the software domain, including code explanation.
State Constrained Stochastic Optimal Control Using LSTMs
In this paper, we propose a new methodology for state constrained stochastic optimal control (SOC) problems.
Bait and Switch: Online Training Data Poisoning of Autonomous Driving Systems
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.
Detecting Backdoors in Neural Networks Using Novel Feature-Based Anomaly Detection
This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers.
Hardware Trojan Detection Using Controlled Circuit Aging
Combining IC aging with over-clocking produces a pattern of bit errors at the IC output by the induced timing violations.
NNoculation: Catching BadNets in the Wild
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.
Adversarial Learning-Based On-Line Anomaly Monitoring for Assured Autonomy
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).
