Search Results for author:
Found 27 papers, 14 papers with code
Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis
This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL), such that the safety constraint violations are bounded at any point during learning.
You Only Explain Once
In this paper, we propose a new black-box explainability algorithm and tool, YO-ReX, for efficient explanation of the outputs of object detectors.
Multiple Different Black Box Explanations for Image Classifiers
Existing explanation tools for image classifiers usually give only a single explanation for an image's classification.
LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning
LCRL is a software tool that implements model-free Reinforcement Learning (RL) algorithms over unknown Markov Decision Processes (MDPs), synthesising policies that satisfy a given linear temporal specification with maximal probability.
Exposing Previously Undetectable Faults in Deep Neural Networks
Existing methods for testing DNNs solve the oracle problem by constraining the raw features (e. g. image pixel values) to be within a small distance of a dataset example for which the desired DNN output is known.
Explanations for Occluded Images
Existing algorithms for explaining the output of image classifiers perform poorly on inputs where the object of interest is partially occluded.
Neural Termination Analysis
We introduce a novel approach to the automated termination analysis of computer programs: we use neural networks to represent ranking functions.
Shielding Atari Games with Bounded Prescience
We present the first exact method for analysing and ensuring the safety of DRL agents for Atari games.
Ranking Policy Decisions
Policies trained via Reinforcement Learning (RL) are often needlessly complex, making them difficult to analyse and interpret.
Cautious Reinforcement Learning with Logical Constraints
This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process.
Evaluating Robustness to Context-Sensitive Feature Perturbations of Different Granularities
We cannot guarantee that training datasets are representative of the distribution of inputs that will be encountered during deployment.
CounterExample Guided Neural Synthesis
Program synthesis is the generation of a program from a specification.
Learning Concise Models from Long Execution Traces
Abstract models of system-level behaviour have applications in design exploration, analysis, testing and verification.
Formal Languages and Automata Theory Software Engineering
DeepSynth: Automata Synthesis for Automatic Task Segmentation in Deep Reinforcement Learning
This paper proposes DeepSynth, a method for effective training of deep Reinforcement Learning (RL) agents when the reward is sparse and non-Markovian, but at the same time progress towards the reward requires achieving an unknown sequence of high-level objectives.
Modular Deep Reinforcement Learning with Temporal Logic Specifications
We propose an actor-critic, model-free, and online Reinforcement Learning (RL) framework for continuous-state continuous-action Markov Decision Processes (MDPs) when the reward is highly sparse but encompasses a high-level temporal structure.
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.
Explaining Image Classifiers using Statistical Fault Localization
The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for "Explainable AI".
Adaptive Generation of Unrestricted Adversarial Inputs
Neural networks are vulnerable to adversarially-constructed perturbations of their inputs.
Certified Reinforcement Learning with Logic Guidance
Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems.
A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
In the past few years, significant progress has been made on deep neural networks (DNNs) in achieving human-level performance on several long-standing tasks.
Logically-Constrained Neural Fitted Q-Iteration
We propose a method for efficient training of Q-functions for continuous-state Markov Decision Processes (MDPs) such that the traces of the resulting policies satisfy a given Linear Temporal Logic (LTL) property.
Concolic Testing for Deep Neural Networks
Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program.
Automatic Heap Layout Manipulation for Exploitation
In this paper we present the first automatic approach to the problem, based on pseudo-random black-box search.
Cryptography and Security Programming Languages
Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the $L_0$ Norm
In this paper we focus on the $L_0$ norm and aim to compute, for a trained DNN and an input, the maximal radius of a safe norm ball around the input within which there are no adversarial examples.
Testing Deep Neural Networks
In this paper, inspired by the MC/DC coverage criterion, we propose a family of four novel test criteria that are tailored to structural features of DNNs and their semantics.
Logically-Constrained Reinforcement Learning
With this reward function, the policy synthesis procedure is "constrained" by the given specification.
Unfolding-based Partial Order Reduction
Over benchmarks with busy-waits, among others, our experiments show a dramatic reduction in the number of executions when compared to a state-of-the-art DPOR.
Logic in Computer Science Programming Languages D.2.4
