Search Results for author:
Found 21 papers, 6 papers with code
Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans
However, IBL relies on simple fixed form functions to capture the mapping from past situations to current decisions.
Bootstrapping Language Models with DPO Implicit Rewards
In this work, we make a novel observation that this implicit reward model can by itself be used in a bootstrapping fashion to further align the LLM.
Probabilistic Perspectives on Error Minimization in Adversarial Reinforcement Learning
To address this challenge, we introduce a novel objective called Adversarial Counterfactual Error (ACoE), which naturally balances optimizing value and robustness against adversarial attacks.
Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning
Many problems in Reinforcement Learning (RL) seek an optimal policy with large discrete multidimensional yet unordered action spaces; these include problems in randomized allocation of resources such as placements of multiple security resources and emergency response units, etc.
Handling Long and Richly Constrained Tasks through Constrained Hierarchical Reinforcement Learning
Safety in goal directed Reinforcement Learning (RL) settings has typically been handled through constraints over trajectories and have demonstrated good performance in primarily short horizon tasks.
BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets
Our experiments conducted on four tasks and four offline RL algorithms expose a disquieting fact: none of the existing offline RL algorithms is immune to such a backdoor attack.
Scalable Distributional Robustness in a Class of Non Convex Optimization with Guarantees
Distributionally robust optimization (DRO) has shown lot of promise in providing robustness in learning as well as sample based optimization problems.
Proceedings of the Artificial Intelligence for Cyber Security (AICS) Workshop at AAAI 2022
These challenges are widely studied in enterprise networks, but there are many gaps in research and practice as well as novel problems in other domains.
The Art of Manipulation: Threat of Multi-Step Manipulative Attacks in Security Games
This paper studies the problem of multi-step manipulative attacks in Stackelberg security games, in which a clever attacker attempts to orchestrate its attacks over multiple time steps to mislead the defender's learning of the attacker's behavior.
Beyond NaN: Resiliency of Optimization Layers in The Face of Infeasibility
We show that an adversary can cause such failures by forcing rank deficiency on the matrix fed to the optimization layer which results in the optimization failing to produce a solution.
Multiscale Generative Models: Improving Performance of a Generative Model Using Feedback from Other Dependent Generative Models
Recent work has used generative models (GANs in particular) for providing high-fidelity simulation of real-world systems.
Measuring Data Collection Diligence for Community Healthcare
In this work, we define and test a data collection diligence score.
Generating Realistic Stock Market Order Streams
We propose an approach to generate realistic and high-fidelity stock market data based on generative adversarial networks (GANs).
Proceedings of the Artificial Intelligence for Cyber Security (AICS) Workshop 2020
Further, cyber security application areas with a particular emphasis on the characterization and deployment of human-machine teaming will be the focus.
AI for Social Impact: Learning and Planning in the Data-to-Deployment Pipeline
With the maturing of AI and multiagent systems research, we have a tremendous opportunity to direct these advances towards addressing complex societal problems.
Solving Online Threat Screening Games using Constrained Action Space Reinforcement Learning
To solve the online problem with a hard bound on risk, we formulate it as a Reinforcement Learning (RL) problem with constraints on the action space (hard bound on risk).
Two Can Play That Game: An Adversarial Evaluation of a Cyber-alert Inspection System
In order to explain this observation, we extend the earlier RL model to a game model and show that there exists defender policies that can be robust against any adversarial policy.
A Learning and Masking Approach to Secure Learning
Finally, we show that a classifier masking method achieved by adding noise to the a neural network's logit output protects against low distortion attacks such as the CW attack.
Towards the Science of Security and Privacy in Machine Learning
Advances in machine learning (ML) in recent years have enabled a dizzying array of applications such as data analytics, autonomous systems, and security diagnostics.
Learning Adversary Behavior in Security Games: A PAC Model Perspective
We provide four main contributions: (1) a PAC model of learning adversary response functions in SSGs; (2) PAC-model analysis of the learning of key, existing bounded rationality models in SSGs; (3) an entirely new approach to adversary modeling based on a non-parametric class of response functions with PAC-model analysis and (4) identification of conditions under which computing the best defender strategy against the learned adversary behavior is indeed the optimal strategy.
Security Games with Information Leakage: Modeling and Computation
Our experiments confirm the necessity of handling information leakage and the advantage of our algorithms.
