Search Results for author:
Found 102 papers, 35 papers with code
Safety Guardrails for LLM-Enabled Robots
Although the integration of large language models (LLMs) into robotics has unlocked transformative capabilities, it has also introduced significant safety concerns, ranging from average-case LLM errors (e. g., hallucinations) to adversarial jailbreaking attacks, which can produce harmful robot behavior in real-world settings.
Domain Randomization is Sample Efficient for Linear Quadratic Control
We study the sample efficiency of domain randomization and robust control for the benchmark problem of learning the linear quadratic regulator (LQR).
PKF: Probabilistic Data Association Kalman Filter for Multi-Object Tracking
We view the unknown data association as a latent variable and apply Expectation Maximization (EM) to obtain a filter with update step in the same form as the Kalman filter but with expanded measurement vector of all potential associations.
Conformal Risk Minimization with Variance Reduction
In this direction, conformal training (ConfTr) by Stutz et al.(2022) is a technique that seeks to minimize the expected prediction set size of a model by simulating CP in-between training updates.
Jailbreaking LLM-Controlled Robots
Unlike existing, textual attacks on LLM chatbots, RoboPAIR elicits harmful physical actions from LLM-controlled robots, a phenomenon we experimentally demonstrate in three scenarios: (i) a white-box setting, wherein the attacker has full access to the NVIDIA Dolphins self-driving LLM, (ii) a gray-box setting, wherein the attacker has partial access to a Clearpath Robotics Jackal UGV robot equipped with a GPT-4o planner, and (iii) a black-box setting, wherein the attacker has only query access to the GPT-3. 5-integrated Unitree Robotics Go2 robot dog.
Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples
We show that when $N \gtrsim C_{\mathrm{dep}} (\mathrm{dim}(\mathcal F) + \mathrm{C}(\mathcal G)/T)$, the excess risk of $\hat f^{(0)} \circ \hat g$ on the target task decays as $\nu_{\mathrm{div}} \big(\frac{\mathrm{dim}(\mathcal F)}{N'} + \frac{\mathrm{C}(\mathcal G)}{N T} \big)$, where $C_{\mathrm{dep}}$ denotes the effect of data dependency, $\nu_{\mathrm{div}}$ denotes an (estimatable) measure of $\textit{task-diversity}$ between the source and target tasks, and $\mathrm C(\mathcal G)$ denotes the complexity of the representation class $\mathcal G$.
Flying Quadrotors in Tight Formations using Learning-based Model Predictive Control
Through simulations and physical experiments, we show that incorporating the model into a novel learning-based nonlinear model predictive control (MPC) framework results in substantial performance improvements in terms of trajectory tracking and disturbance rejection.
SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments
However, existing LLM-enabled planners typically do not consider online planning or complex missions; rather, relevant subtasks and semantics are provided by a pre-built map or a user.
State space models, emergence, and ergodicity: How many parameters are needed for stable predictions?
For this situation, we show that there exists no learner using a linear filter which can succesfully learn the random walk unless the filter length exceeds a certain threshold depending on the effective memory length and horizon of the problem.
Formal Verification and Control with Conformal Prediction
We focus on learning-enabled autonomous systems (LEASs) in which the complexity of learning-enabled components (LECs) is a major bottleneck that hampers the use of existing model-based verification and design techniques.
CViT: Continuous Vision Transformer for Operator Learning
Here we introduce the Continuous Vision Transformer (CViT), a novel neural operator architecture that leverages advances in computer vision to address challenges in learning complex physical systems.
Recursively Feasible Shrinking-Horizon MPC in Dynamic Environments with Conformal Prediction Guarantees
We propose a shrinking-horizon MPC that guarantees recursive feasibility via a gradual relaxation of the safety constraints as new prediction regions become available online.
Active Learning for Control-Oriented Identification of Nonlinear Systems
Model-based reinforcement learning is an effective approach for controlling an unknown system.
Rate-Optimal Non-Asymptotics for the Quadratic Prediction Error Method
We study the quadratic prediction error method -- i. e., nonlinear least squares -- for a class of time-varying parametric predictor models satisfying a certain identifiability condition.
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
To address these challenges, we introduce JailbreakBench, an open-sourced benchmark with the following components: (1) an evolving repository of state-of-the-art adversarial prompts, which we refer to as jailbreak artifacts; (2) a jailbreaking dataset comprising 100 behaviors -- both original and sourced from prior work (Zou et al., 2023; Mazeika et al., 2023, 2024) -- which align with OpenAI's usage policies; (3) a standardized evaluation framework at https://github. com/JailbreakBench/jailbreakbench that includes a clearly defined threat model, system prompts, chat templates, and scoring functions; and (4) a leaderboard at https://jailbreakbench. github. io/ that tracks the performance of attacks and defenses for various LLMs.
Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
Prompt engineering is effective for controlling the output of text-to-image (T2I) generative models, but it is also laborious due to the need for manually crafted prompts.
DASA: Delay-Adaptive Multi-Agent Stochastic Approximation
We consider a setting in which $N$ agents aim to speedup a common Stochastic Approximation (SA) problem by acting in parallel and communicating with a central server.
Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content.
Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling
Motivated by applications in large-scale and multi-agent reinforcement learning, we study the non-asymptotic performance of stochastic approximation (SA) schemes with delayed updates under Markovian sampling.
Sharp Rates in Dependent Learning Theory: Avoiding Sample Size Deflation for the Square Loss
In this work, we study statistical learning with dependent ($\beta$-mixing) data and square loss in a hypothesis class $\mathscr{F}\subset L_{\Psi_p}$ where $\Psi_p$ is the norm $\|f\|_{\Psi_p} \triangleq \sup_{m\geq 1} m^{-1/p} \|f\|_{L^m} $ for some $p\in [2,\infty]$.
Learning Local Control Barrier Functions for Hybrid Systems
Our approach is computationally efficient, minimally invasive to any reference controller, and applicable to large-scale systems.
Multi-Modal Conformal Prediction Regions with Simple Structures by Optimizing Convex Shape Templates
While prior work has gone into creating score functions that produce multi-model prediction regions, such regions are generally too complex for use in downstream planning and control problems.
Data-Driven Modeling and Verification of Perception-Based Autonomous Systems
This paper addresses the problem of data-driven modeling and verification of perception-based autonomous systems.
Jailbreaking Black Box Large Language Models in Twenty Queries
PAIR -- which is inspired by social engineering attacks -- uses an attacker LLM to automatically generate jailbreaks for a separate targeted LLM without human intervention.
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
Despite efforts to align large language models (LLMs) with human intentions, widely-used LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generating objectionable content.
Structural Risk Minimization for Learning Nonlinear Dynamics
We empirically show that even though too loose to be used as absolute estimates, our SRM bounds on the true prediction error are able to track its relative behavior across different model classes of the hierarchy.
A Tutorial on the Non-Asymptotic Theory of System Identification
This tutorial serves as an introduction to recently developed non-asymptotic methods in the theory of -- mainly linear -- system identification.
Safety Filter Design for Neural Network Systems via Convex Optimization
With the increase in data availability, it has been widely demonstrated that neural networks (NN) can capture complex system dynamics precisely in a data-driven manner.
Adversarial Training Should Be Cast as a Non-Zero-Sum Game
One prominent approach toward resolving the adversarial vulnerability of deep neural networks is the two-player zero-sum paradigm of adversarial training, in which predictors are trained against adversarially chosen perturbations of data.
Combined Left and Right Temporal Robustness for Control under STL Specifications
Many modern autonomous systems, particularly multi-agent systems, are time-critical and need to be robust against timing uncertainties.
Physics-enhanced Gaussian Process Variational Autoencoder
Variational autoencoders allow to learn a lower-dimensional latent space based on high-dimensional input/output data.
Learning Switching Port-Hamiltonian Systems with Uncertainty Quantification
Switching physical systems are ubiquitous in modern control applications, for instance, locomotion behavior of robots and animals, power converters with switches and diodes.
Gaussian Process Port-Hamiltonian Systems: Bayesian Learning with Physics Prior
Data-driven approaches achieve remarkable results for the modeling of complex dynamics based on collected data.
Federated TD Learning over Finite-Rate Erasure Channels: Linear Speedup under Markovian Sampling
Federated learning (FL) has recently gained much attention due to its effectiveness in speeding up supervised learning tasks under communication and privacy constraints.
Conformal Prediction Regions for Time Series using Linear Complementarity Programming
In fact, to obtain prediction regions over $T$ time steps with confidence $1-\delta$, {previous works require that each individual prediction region is valid} with confidence $1-\delta/T$.
Safe Perception-Based Control under Stochastic Sensor Uncertainty using Conformal Prediction
However, these perception maps are not perfect and result in state estimation errors that can lead to unsafe system behavior.
Variational Autoencoding Neural Operators
Unsupervised learning with functional data is an emerging paradigm of machine learning research with applications to computer vision, climate modeling and physical systems.
Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity
We initiate the study of federated reinforcement learning under environmental heterogeneity by considering a policy evaluation problem.
Certified Invertibility in Neural Networks via Mixed-Integer Programming
Neural networks are known to be vulnerable to adversarial attacks, which are small, imperceptible perturbations that can significantly alter the network's output.
Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning
These works have collectively revealed that stochastic gradient descent (SGD) is robust to structured perturbations such as quantization, sparsification, and delays.
Conformal Prediction for STL Runtime Verification
The second algorithm constructs prediction regions for future system states first, and uses these to obtain a prediction region for the satisfaction measure.
Graph Neural Networks for Multi-Robot Active Information Acquisition
This paper addresses the Multi-Robot Active Information Acquisition (AIA) problem, where a team of mobile robots, communicating through an underlying graph, estimates a hidden state expressing a phenomenon of interest.
Statistical Learning Theory for Control: A Finite Sample Perspective
This tutorial survey provides an overview of recent non-asymptotic advances in statistical learning theory as relevant to control and system identification.
Secure state estimation over Markov wireless communication channels (extended version)
This note studies state estimation in wireless networked control systems with secrecy against eavesdropping.
Probable Domain Generalization via Quantile Risk Minimization
By minimizing the $\alpha$-quantile of predictor's risk distribution over domains, QRM seeks predictors that perform well with probability $\alpha$.
NOMAD: Nonlinear Manifold Decoders for Operator Learning
Supervised learning in function spaces is an emerging area of machine learning research with applications to the prediction of complex physical systems such as fluid flows, solid mechanics, and climate modeling.
Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds
We consider a linear stochastic bandit problem involving $M$ agents that can collaborate via a central server to minimize regret.
Risk of Stochastic Systems for Temporal Logic Specifications
For discrete-time stochastic processes, we show under which conditions the approximate STL robustness risk can even be computed exactly.
Learning to Control Linear Systems can be Hard
In this paper, we study the statistical difficulty of learning to control linear systems.
Distributed Statistical Min-Max Learning in the Presence of Byzantine Agents
Recent years have witnessed a growing interest in the topic of min-max optimization, owing to its relevance in the context of generative adversarial networks (GANs), robust control and optimization, and reinforcement learning.
Adaptive Stochastic MPC under Unknown Noise Distribution
Then, we employ this benchmark controller to derive a novel robustly stable adaptive SMPC scheme that learns the necessary noise statistics online, while guaranteeing time-uniform satisfaction of the unknown reformulated state constraints with high probability.
Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks
Lipschitz constants of neural networks allow for guarantees of robustness in image classification, safety in controller design, and generalizability beyond the training data.
Temporal Robustness of Temporal Logic Specifications: Analysis and Control Design
We study the temporal robustness of temporal logic specifications and show how to design temporally robust control laws for time-critical control systems.
Do Deep Networks Transfer Invariances Across Classes?
Based on this analysis, we show how a generative approach for learning the nuisance transformations can help transfer invariances across classes and improve performance on a set of imbalanced image classification benchmarks.
Ranked #23 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Linear Stochastic Bandits over a Bit-Constrained Channel
Specifically, in our setup, an agent interacting with an environment transmits encoded estimates of an unknown model parameter to a server over a communication channel of finite capacity.
Temporal Robustness of Stochastic Signals
We then define the temporal robustness risk by investigating the temporal robustness of the realizations of a stochastic signal.
Probabilistically Robust Learning: Balancing Average- and Worst-case Performance
From a theoretical point of view, this framework overcomes the trade-offs between the performance and the sample-complexity of worst-case and average-case learning.
Learning Operators with Coupled Attention
Supervised operator learning is an emerging machine learning paradigm with applications to modeling the evolution of spatio-temporal dynamical systems and approximating general black-box relationships between functional data.
Learning Rigidity-based Flocking Control with Gaussian Processes
We provide a decentralized control law that exponentially stabilizes the motion of the agents and captures Reynolds boids motion for swarms by using GPs as an online learning-based oracle for the prediction of the unknown dynamics.
Adversarial Robustness with Semi-Infinite Constrained Learning
In particular, we leverage semi-infinite optimization and non-convex duality theory to show that adversarial training is equivalent to a statistical problem over perturbation distributions, which we characterize completely.
Learning Region of Attraction for Nonlinear Systems
Estimating the region of attraction (ROA) of general nonlinear autonomous systems remains a challenging problem and requires a case-by-case analysis.
Reactive and Risk-Aware Control for Signal Temporal Logic
Addressing these is pivotal to build fully autonomous systems and requires a systematic integration of planning and control.
Safe Pontryagin Differentiable Programming
We propose a Safe Pontryagin Differentiable Programming (Safe PDP) methodology, which establishes a theoretical and algorithmic framework to solve a broad class of safety-critical learning and control tasks -- problems that require the guarantee of safety constraint satisfaction at any stage of the learning and control progress.
Time-Robust Control for STL Specifications
We present a robust control framework for time-critical systems in which satisfying real-time constraints robustly is of utmost importance for the safety of the system.
STL Robustness Risk over Discrete-Time Stochastic Processes
We then define the risk of a stochastic process not satisfying an STL formula robustly, referred to as the STL robustness risk.
Linear Systems can be Hard to Learn
Statistically easy to learn linear system classes have sample complexity that is polynomial with the system dimension.
Model-Based Domain Generalization
Despite remarkable success in a variety of applications, it is well-known that deep learning can fail catastrophically when presented with out-of-distribution data.
Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients
We consider a standard federated learning (FL) architecture where a group of clients periodically coordinate with a central server to train a statistical model.
Learning Lyapunov Functions for Hybrid Systems
By designing the learner and the verifier according to the analytic center cutting-plane method from convex optimization, we show that when the set of Lyapunov functions is full-dimensional in the parameter space, our method finds a Lyapunov function in a finite number of steps.
Optimization and Control
Is the brain macroscopically linear? A system identification of resting state dynamics
Contrary to our expectations, linear auto-regressive models achieve the best measures across all three metrics, eliminating the trade-off between accuracy and simplicity.
Scalable Reinforcement Learning Policies for Multi-Agent Control
Our method can handle an arbitrary number of pursuers and targets; we show results for tasks consisting up to 1000 pursuers tracking 1000 targets.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Control Barrier Functions for Unknown Nonlinear Systems using Gaussian Processes
This paper focuses on the controller synthesis for unknown, nonlinear systems while ensuring safety constraints.
Online learning-based trajectory tracking for underactuated vehicles with uncertain dynamics
To overcome this issue, we present a tracking control law for underactuated rigid-body dynamics using an online learning-based oracle for the prediction of the unknown dynamics.
Learning to Track Dynamic Targets in Partially Known Environments
In particular, we introduce Active Tracking Target Network (ATTN), a unified RL policy that is capable of solving major sub-tasks of active target tracking -- in-sight tracking, navigation, and exploration.
Zeroth-order Deterministic Policy Gradient
Deterministic Policy Gradient (DPG) removes a level of randomness from standard randomized-action Policy Gradient (PG), and demonstrates substantial empirical success for tackling complex dynamic problems involving Markov decision processes.
Model-Based Robust Deep Learning: Generalizing to Natural, Out-of-Distribution Data
Indeed, natural variation such as lighting or weather conditions can significantly degrade the accuracy of trained neural networks, proving that such natural variation presents a significant challenge for deep learning.
Teaching Recurrent Neural Networks to Modify Chaotic Memories by Example
Here we demonstrate that a recurrent neural network (RNN) can learn to modify its representation of complex information using only examples, and we explain the associated learning mechanism with new theory.
Robust Deep Learning as Optimal Control: Insights and Convergence Guarantees
By interpreting the min-max problem as an optimal control problem, it has recently been shown that one can exploit the compositional structure of neural networks in the optimization problem to improve the training time significantly.
Reach-SDP: Reachability Analysis of Closed-Loop Systems with Neural Network Controllers via Semidefinite Programming
There has been an increasing interest in using neural networks in closed-loop control systems to improve performance and reduce computational costs for on-line implementation.
Sample Complexity of Kalman Filtering for Unknown Systems
We show that when the system identification step produces sufficiently accurate estimates, or when the underlying true KF is sufficiently robust, that a Certainty Equivalent (CE) KF, i. e., one designed using the estimated parameters directly, enjoys provable sub-optimality guarantees.
Risk-Aware MMSE Estimation
Despite the simplicity and intuitive interpretation of Minimum Mean Squared Error (MMSE) estimators, their effectiveness in certain scenarios is questionable.
Model-Free Learning of Optimal Ergodic Policies in Wireless Systems
Upon further assuming the use of near-universal policy parameterizations, we also develop explicit bounds on the gap between optimal values of initial, infinite dimensional resource allocation problems, and dual values of their parameterized smoothed surrogates.
Statistical Learning for Analysis of Networked Control Systems over Unknown Channels
In this regard our work is the first to characterize the amount of channel modeling that is required to answer such a question.
Learning Q-network for Active Information Acquisition
In this paper, we propose a novel Reinforcement Learning approach for solving the Active Information Acquisition problem, which requires an agent to choose a sequence of actions in order to acquire information about a process of interest using on-board sensors.
Probabilistic Verification and Reachability Analysis of Neural Networks via Semidefinite Programming
In this context, we discuss two relevant problems: (i) probabilistic safety verification, in which the goal is to find an upper bound on the probability of violating a safety specification; and (ii) confidence ellipsoid estimation, in which given a confidence ellipsoid for the input of the neural network, our goal is to compute a confidence ellipsoid for the output.
Distributed Attack-Robust Submodular Maximization for Multi-Robot Planning
Since, DRM overestimates the number of attacks in each clique, in this paper we also introduce an Improved Distributed Robust Maximization (IDRM) algorithm.
Optimal Algorithms for Submodular Maximization with Distributed Constraints
Given this distributed setting, we develop Constraint-Distributed Continuous Greedy (CDCG), a message passing algorithm that converges to the tight $(1-1/e)$ approximation factor of the optimum global solution using only local computation and communication.
Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guarantees
Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology.
Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks
The resulting SDP can be adapted to increase either the estimation accuracy (by capturing the interaction between activation functions of different layers) or scalability (by decomposition and parallel implementation).
Finite Sample Analysis of Stochastic System Identification
In this paper, we analyze the finite sample complexity of stochastic system identification using modern tools from machine learning and statistics.
Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
Certifying the safety or robustness of neural networks against input uncertainties and adversarial attacks is an emerging challenge in the area of safe machine learning and control.
Network Design for Controllability Metrics
In this setting, we first consider a feasibility problem consisting of tuning the edge weights such that certain controllability properties are satisfied.
Optimization and Control
Verisig: verifying safety properties of hybrid systems with neural network controllers
This paper presents Verisig, a hybrid system approach to verifying safety properties of closed-loop systems using neural networks as controllers.
Systems and Control
Cloud-based Quadratic Optimization with Partially Homomorphic Encryption
The development of large-scale distributed control systems has led to the outsourcing of costly computations to cloud-computing platforms, as well as to concerns about privacy of the collected sensitive data.
Optimization and Control Cryptography and Security Systems and Control
Resilient Non-Submodular Maximization over Matroid Constraints
The objective of this paper is to focus on resilient matroid-constrained problems arising in control and sensing but in the presence of sensor and actuator failures.
Cloud-based MPC with Encrypted Data
We propose protocols for two cloud-MPC architectures motivated by the current developments in the Internet of Things: a client-server architecture and a two-server architecture.
Optimization and Control Cryptography and Security Systems and Control
Resilient Active Information Gathering with Mobile Robots
In this paper, we provide the first algorithm, enabling the following capabilities: minimal communication, i. e., the algorithm is executed by the robots based only on minimal communication between them; system-wide resiliency, i. e., the algorithm is valid for any number of denial-of-service attacks and failures; and provable approximation performance, i. e., the algorithm ensures for all monotone (and not necessarily submodular) objective functions a solution that is finitely close to the optimal.
Resilient Monotone Sequential Maximization
In this paper, we provide the first scalable algorithm, that achieves the following characteristics: system-wide resiliency, i. e., the algorithm is valid for any number of denial-of-service attacks, deletions, or failures; adaptiveness, i. e., at each time step, the algorithm selects system elements based on the history of inflicted attacks, deletions, or failures; and provable approximation performance, i. e., the algorithm guarantees for monotone objective functions a solution close to the optimal.
Dense 3-D Mapping with Spatial Correlation via Gaussian Filtering
Many accurate and efficient methods exist that address this problem but most assume that the occupancy states of different elements in the map representation are statistically independent.
Robotics
Assumed Density Filtering Q-learning
We formulate an efficient closed-form solution for the value update by approximately estimating analytic parameters of the posterior of the Q-beliefs.
Active Deformable Part Models
This paper presents an active approach for part-based object detection, which optimizes the order of part filter evaluations and the time at which to stop and make a prediction.
Nonmyopic View Planning for Active Object Detection
One of the central problems in computer vision is the detection of semantically important objects and the estimation of their pose.
