相关论文: Formal Verification of a Distributed Dynamic Recon…
This paper describes REALab, a platform for embedded agency research in reinforcement learning (RL). REALab is designed to model the structure of tampering problems that may arise in real-world deployments of RL. Standard Markov Decision…
Today's massive AI computation loads push heavy data synchronization across sites, i.e., nodes in data centers. Any reduction in such consensus latency can significantly improve the overall performance of desired systems. This consensus…
Operating effectively in complex environments while complying with specified constraints is crucial for the safe and successful deployment of robots that interact with and operate around people. In this work, we focus on generating…
The last decade has sparked several valiant efforts in deductive verification of distributed agreement protocols such as consensus and leader election. Oddly, there have been far fewer verification efforts that go beyond the core protocols…
While directly fine-tuning (FT) large-scale, pretrained models on task-specific data is well-known to induce strong in-distribution task performance, recent works have demonstrated that different adaptation protocols, such as linear probing…
In the age of data revolution, a modern storage~or transmission system typically requires different levels of protection. For example, the coding technique used to fortify data in a modern storage system when the device is fresh cannot be…
This paper considers the problem of online multi-robot motion planning with general nonlinear dynamics subject to unknown external disturbances. We propose dSLAP, a distributed safe learning and planning framework that allows the robots to…
Distributed agreement-based (DAB) systems use common distributed agreement protocols such as leader election and consensus as building blocks for their target functionality. While automated verification for DAB systems is undecidable in…
Proof-of-stake blockchains require consensus protocols that support Dynamic Availability and Reconfiguration (so-called DAR setting), where the former means that the consensus protocol should remain live even if a large number of nodes…
For lattice modular self-reconfigurable robots (MSRRs), maintaining stable connections during reconfiguration is crucial for physical feasibility and deployability. This letter presents a novel self-reconfiguration planning algorithm for…
Due to limited resources and public safety concerns, deep reinforcement learning (RL) agents for many cyber-physical systems (e.g., autonomous vehicles) are first trained in simulators. However, when deployed in real world environments,…
In large-scale networks of uncertain dynamical systems, where communication is limited and there is a strong interaction among subsystems, learning local models and control policies offers great potential for designing high-performance…
Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of control problems. However, applications in safety-critical domains require a systematic and formal approach to specifying…
This paper introduces Fast Linearized Adaptive Policy (FLAP), a new meta-reinforcement learning (meta-RL) method that is able to extrapolate well to out-of-distribution tasks without the need to reuse data from training, and adapt almost…
Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text inputs, revealing a persistent multimodal safety gap. We study this gap from a…
This paper presents a Hoare-style calculus for formal reasoning about reconfiguration programs of distributed systems. Such programs create and delete components and/or interactions (connectors) while the system components change state…
Power distribution networks are evolving due to the integration of DERs and increased customer participation. To maintain optimal operation, minimize losses, and meet varying load demands, frequent network reconfiguration is necessary.…
The application of reinforcement learning to safety-critical systems is limited by the lack of formal methods for verifying the robustness and safety of learned policies. This paper introduces a novel framework that addresses this gap by…
Replay and rollback attacks threaten cloud application integrity by reintroducing authentic yet stale data through an untrusted storage interface to compromise application decision-making. Prior security frameworks mitigate these attacks by…
The increasing penetration of renewable generation and the growing variability of electrified demand introduce substantial operational uncertainty to modern power systems. Topology reconfiguration is widely recognized as an effective and…