Search Results for author:
Found 14 papers, 3 papers with code
Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations
Existing solutions either introduce a regularization term to improve the smoothness of the trained policy against perturbations or alternatively train the agent's policy and the attacker's policy.
Enhancing LLM Safety via Constrained Direct Preference Optimization
Empirically, our approach provides a safety guarantee to LLMs that is missing in DPO while achieving significantly higher rewards under the same safety constraint compared to a recently proposed safe RLHF approach.
A First Order Meta Stackelberg Method for Robust Federated Learning
Previous research has shown that federated learning (FL) systems are exposed to an array of security risks.
Learning to Backdoor Federated Learning
In particular, we propose a general reinforcement learning-based backdoor attack framework where the attacker first trains a (non-myopic) attack policy using a simulator built upon its local data and common knowledge on the FL system, which is then applied during actual FL training.
Online Learning for Adaptive Probing and Scheduling in Dense WLANs
The problem is challenging even when the link rate distributions are pre-known (the offline setting) due to the necessity of balancing the information gains from probing and the cost of reducing the data transmission opportunity.
Pandering in a Flexible Representative Democracy
We introduce a novel formal model of \emph{pandering}, or strategic preference reporting by candidates seeking to be elected, and examine the resilience of two democratic voting systems to pandering within a single round and across multiple rounds.
Coordinated Attacks Against Federated Learning: A Multi-Agent Reinforcement Learning Approach
We propose a model-based multi-agent reinforcement learning attack framework against federated learning systems.
Privacy Protected Multi-Domain Collaborative Learning
Unsupervised domain adaptation (UDA) aims to transfer knowledge from one or more well-labeled source domains to improve model performance on the different-yet-related target domain without any annotations.
Joint AP Probing and Scheduling: A Contextual Bandit Approach
In contrast to traditional link scheduling problems under uncertainty, we assume that in each time step, the device can probe a subset of links before deciding which one to use.
Robust Sequence Submodular Maximization
Compared to robust submodular maximization for set function, new challenges arise when sequence functions are concerned.
Structure Matters: Towards Generating Transferable Adversarial Images
In this paper, we propose the novel concepts of structure patterns and structure-aware perturbations that relax the small perturbation constraint while still keeping images natural.
Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples
A common requirement in all these works is that the malicious perturbations should be small enough (measured by an L_p norm for some p) so that they are imperceptible to humans.
Analysis of Thompson Sampling for Graphical Bandits Without the Graphs
To fill this gap, we propose a variant of Thompson Sampling, that attains the optimal regret in the directed setting within a logarithmic factor.
When to Reset Your Keys: Optimal Timing of Security Updates via Learning
As these attacks are often designed to disable a system (or a critical resource, e. g., a user account) repeatedly, it is crucial for the defender to keep updating its security measures to strike a balance between the risk of being compromised and the cost of security updates.
