46 citations · 115 across the 40 of their papers we have counts for
16 papers · 1 filter
Certified Robustness via Sparse Second-Order Cone Relaxations
Mohammadreza Maleki, Daniel Sadig, Rushendra Sidibomma +3
Certified robustness is critical for deploying neural networks in safety-sensitive settings, but computing exact certificates typically requires solving nonconvex optimization prob…
Minimally Invasive Steering of Language Models
Taha Entesari, Jingyu Zhang, Daniel Khashabi +1
Pre-logit steering adapts a frozen language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the…
Beyond Average Safety: Chance-Constrained LLM Fine-tuning
Taha Entesari, Mahyar Fazlyab
Fine-tuning large language models on new objectives can improve helpfulness, instruction following, or domain-specific performance, but it can also induce regressions on safety-cri…
Hierarchical End-to-End Taylor Bounds for Complete Neural Network Verification
Taha Entesari, Mahyar Fazlyab
Reachability analysis of neural networks, which seeks to compute or bound the set of outputs attainable over a given input domain, is central to certifying safety and robustness in…
Compositional Curvature Bounds for Deep Neural Networks
Taha Entesari, Sina Sharifi, Mahyar Fazlyab
A key challenge that threatens the widespread use of neural networks in safety-critical applications is their vulnerability to adversarial attacks. In this paper, we study the seco…
Provable Bounds on the Hessian of Neural Networks: Derivative-Preserving Reachability Analysis
Sina Sharifi, Mahyar Fazlyab
We propose a novel reachability analysis method tailored for neural networks with smooth activations. Our method relies on constructing an end-to-end first-order Taylor expansion o…
Verification-Aided Learning of Neural Network Barrier Functions with Termination Guarantees
Shaoru Chen, Lekan Molu, Mahyar Fazlyab
Barrier functions are a general framework for establishing a safety guarantee for a system. However, there is no general method for finding these functions. To address this shortco…
Actor-Critic Physics-informed Neural Lyapunov Control
Jiarui Wang, Mahyar Fazlyab
Designing control policies for stabilization tasks with provable guarantees is a long-standing problem in nonlinear control. A crucial performance metric is the size of the resulti…
Learning Performance-Oriented Control Barrier Functions Under Complex Safety Constraints and Limited Actuation
Lakshmideepakreddy Manda, Shaoru Chen, Mahyar Fazlyab
Control Barrier Functions (CBFs) provide an elegant framework for constraining nonlinear control system dynamics to remain within an invariant subset of a designated safe set. Howe…
Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
Mahyar Fazlyab, Taha Entesari, Aniket Roy +1
To improve the robustness of deep classifiers against adversarial perturbations, many approaches have been proposed, such as designing new architectures with better robustness prop…
Certified Invertibility in Neural Networks via Mixed-Integer Programming
Tianqi Cui, Thomas Bertalan, George J. Pappas +3
Neural networks are known to be vulnerable to adversarial attacks, which are small, imperceptible perturbations that can significantly alter the network's output. Conversely, there…
DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting
Shaoru Chen, Eric Wong, J. Zico Kolter +1
Analyzing the worst-case performance of deep neural networks against input perturbations amounts to solving a large-scale non-convex optimization problem, for which several past wo…
Performance Bounds for Neural Network Estimators: Applications in Fault Detection
Navid Hashemi, Mahyar Fazlyab, Justin Ruths
We exploit recent results in quantifying the robustness of neural networks to input variations to construct and tune a model-based anomaly detector, where the data-driven estimator…
Certifying Incremental Quadratic Constraints for Neural Networks via Convex Optimization
Navid Hashemi, Justin Ruths, Mahyar Fazlyab
Abstracting neural networks with constraints they impose on their inputs and outputs can be very useful in the analysis of neural network classifiers and to derive optimization-bas…
Enforcing robust control guarantees within neural network policies
Priya L. Donti, Melrose Roderick, Mahyar Fazlyab +1
When designing controllers for safety-critical systems, practitioners often face a challenging tradeoff between robustness and performance. While robust control methods provide rig…
Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks
Mahyar Fazlyab, Alexander Robey, Hamed Hassani +2
Tight estimation of the Lipschitz constant for deep neural networks (DNNs) is useful in many applications ranging from robustness certification of classifiers to stability analysis…