A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
The paper tackles safe exploration in RL by a conservative safety critic.
Safe RL with binary feedback using SABRE algorithm.
PAC-Wrap provides provable guarantees for semi-supervised anomaly detection.
Artificial Neural Networks (ANNs) have demonstrated remarkable utility in various challenging machine learning applications. While formally verified properties of their behaviors are highly desired, they have proven notoriously difficult to derive and enforce. Existing approaches typically formulate this problem as a p…
ASE safely explores unknown MDPs with unknown dynamics, improving sample efficiency.
Framework for safely updating machine learning models.
Recent successes in reinforcement learning have lead to the development of complex controllers for real-world robots. As these robots are deployed in safety-critical applications and interact with humans, it becomes critical to ensure safety in order to avoid causing harm. A first step in this direction is to test the …
New algorithm optimizes reward while ensuring safety in complex decision-making problems.
The paper certifies neural network-based control barrier functions efficiently.
Paper reviews robustness in machine learning models and discusses training and certification methods.
Classifier-based AI safety gates fail in self-improvement, even with advanced verification methods.
It has been shown that neural network classifiers are not robust. This raises concerns about their usage in safety-critical systems. We propose in this paper a regularization scheme for ReLU networks which provably improves the robustness of the classifier by maximizing the linear regions of the classifier as well as t…
Paper proposes a method to predict deep neural network confidences with guarantees.
New algorithm achieves sublinear regret in CMDPs without error cancellations.
Despite the improved accuracy of deep neural networks, the discovery of adversarial examples has raised serious safety concerns. In this paper, we study two variants of pointwise robustness, the maximum safe radius problem, which for a given input sample computes the minimum distance to an adversarial example, and the …
Revel tackles safe exploration in RL with verified symbolic policies.
We study the problem of safe learning and exploration in sequential control problems. The goal is to safely collect data samples from operating in an environment, in order to learn to achieve a challenging control goal (e.g., an agile maneuver close to a boundary). A central challenge in this setting is how to quantify…
While deep reinforcement learning has successfully solved many challenging control tasks, its real-world applicability has been limited by the inability to ensure the safety of learned policies. We propose an approach to verifiable reinforcement learning by training decision tree policies, which can represent complex p…
Approach to verify neural network training integrity.
Improves safety region certification for smoothed classifiers without changing smoothing scheme.
Gaussian Processes (GPs) are widely employed in control and learning because of their principled treatment of uncertainty. However, tracking uncertainty for iterative, multi-step predictions in general leads to an analytically intractable problem. While approximation methods exist, they do not come with guarantees, mak…
Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world systems. As a consequence, learning algorithms are rarely applied on safety-crit…
It has recently been shown that ReLU networks produce arbitrarily over-confident predictions far away from the training data. Thus, ReLU networks do not know when they don't know. However, this is a highly important property in safety critical applications. In the context of out-of-distribution detection (OOD) there ha…
CoCoRL learns safe constraints from demonstrations with unknown rewards.
In Interactive Machine Learning (IML), we iteratively make decisions and obtain noisy observations of an unknown function. While IML methods, e.g., Bayesian optimization and active learning, have been successful in applications, on real-world systems they must provably avoid unsafe decisions. To this end, safe IML algo…
RLVR maintains safety while improving reasoning capabilities in LLMs.
Robustness is important for sequential decision making in a stochastic dynamic environment with uncertain probabilistic parameters. We address the problem of using robust MDPs (RMDPs) to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution is det…
Machine learning (ML) classification is increasingly used in safety-critical systems. Protecting ML classifiers from adversarial examples is crucial. We propose that the main threat is that of an attacker perturbing a confidently classified input to produce a confident misclassification. To protect against this we devi…
Robust MDPs (RMDPs) can be used to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution are determined by the ambiguity set---the set of plausible transition probabilities---which is usually constructed as a multi-dimensional confidence region. E…
Deployment of deep neural networks (DNNs) in safety- or security-critical systems requires provable guarantees on their correct behaviour. A common requirement is robustness to adversarial perturbations in a neighbourhood around an input. In this paper we focus on the norm and aim to compute, for a trained DNN an…
The paper discusses safety assessment for AI systems, focusing on machine learning models.
Proposes new convex relaxations for certifying spatial robustness of neural networks.
Autonomous vehicles rely on machine learning to solve challenging tasks in perception and motion planning. However, automotive software safety standards have not fully evolved to address the challenges of machine learning safety such as interpretability, verification, and performance limitations. In this paper, we revi…
Fine-tuning LLMs improves capability but harms safety, study finds.
A new framework promotes trustworthy user-generated datasets by ensuring no user benefits from misreporting.
Paper tackles robust MDPs with sample complexity guarantees.
RAGuard improves safety in LLMs for offshore wind maintenance.
Survey of algorithms for testing AI-driven CPS safety.
Safe imitation learning with a safety layer for flexible training.
Deep learning methods are widely regarded as indispensable when it comes to designing perception pipelines for autonomous agents such as robots, drones or automated vehicles. The main reasons, however, for deep learning not being used for autonomous agents at large scale already are safety concerns. Deep learning appro…
This paper formalizes AI safety using hypothesis testing in GenAI.
A new algorithm for identifying the best arm in linear feedback with safety constraints.
Safety filter for unknown discrete-time systems with learned models and noise covariance.
SafeML monitors ML systems for safety and security risks.
Paper defines and quantifies safety risks in deep neural networks.
Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic reachability problem for feed-forward DNNs which, for a given set of inputs to the network and a Lipschitz-continuous function over its outputs, computes the lower and upper bound on the function values. Because the network and the …
Study best arm identification with safety constraints in bandit problems.
Failures are challenging for learning to control physical systems since they risk damage, time-consuming resets, and often provide little gradient information. Adding safety constraints to exploration typically requires a lot of prior knowledge and domain expertise. We present a safety measure which implicitly captures…