Presents a successive convexification framework that enforces continuous-time STL specifications in trajectory optimization via GMSR robustness and prox-convex solving.
In: AAAI
9 Pith papers cite this work, alongside 36 external citations. Polarity classification is still indexing.
9
Pith papers citing it
36
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 9roles
background 1polarities
unclear 1representative citing papers
New framework for probabilistic safety shields in MDPs showing impossibility of strong classical guarantees and providing weaker but usable alternatives with offline and online constructions.
A process algebra with guarded choice and recursion is compiled to global and then projected local Mealy machines that filter safe joint actions for each agent in Dec-POMDPs using belief-style state subsets.
Shield synthesis is repositioned as a design-time defensibility analysis framework for adversarial networks, generating verdicts, winning regions, and fingerprints that separate formal safety from operational behavior under adaptive play.
The paper presents a threat model, taxonomy, and six-dimension measurement framework for AI sandboxes to clarify valid testing claims for safety, security, and regulatory assurance.
PaCo-VLA adds an independent passivity shield to VLA outputs so that semantic proposals for compliance and admittance can be used in contact-rich tasks without violating passivity or causing damage.
A governed upgrade framework with interface, policy, behavioral, and recovery checks keeps unsafe activations at zero across multi-round AI capability upgrades on a PyBullet/ROS 2 manipulation testbed while retaining task success near naive upgrades.
A hybrid DRL system for multi-pair crypto trading with deterministic risk shielding outperforms a heuristic baseline at 10% significance on Binance futures data.
A survey that maps risks along the agent workflow and consolidates metrics and benchmarks for safety, robustness, privacy, and security in agentic AI.
citing papers explorer
-
Successive Convexification for Trajectory Optimization with Continuous-time Satisfaction of Signal Temporal Logic Specifications
Presents a successive convexification framework that enforces continuous-time STL specifications in trajectory optimization via GMSR robustness and prox-convex solving.
-
Shields to Guarantee Probabilistic Safety in MDPs
New framework for probabilistic safety shields in MDPs showing impossibility of strong classical guarantees and providing weaker but usable alternatives with offline and online constructions.
-
Generating Local Shields for Decentralised Partially Observable Markov Decision Processes
A process algebra with guarded choice and recursion is compiled to global and then projected local Mealy machines that filter safe joint actions for each agent in Dec-POMDPs using belief-style state subsets.
-
Beyond Runtime Enforcement: Shield Synthesis as Defensibility Analysis for Adversarial Networks
Shield synthesis is repositioned as a design-time defensibility analysis framework for adversarial networks, generating verdicts, winning regions, and fingerprints that separate formal safety from operational behavior under adaptive play.
-
AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework
The paper presents a threat model, taxonomy, and six-dimension measurement framework for AI sandboxes to clarify valid testing claims for safety, security, and regulatory assurance.
-
PaCo-VLA: Passivity-Shielded Compliance Prior for Contact-Rich Vision-Language-Action Manipulation
PaCo-VLA adds an independent passivity shield to VLA outputs so that semantic proposals for compliance and admittance can be used in contact-rich tasks without violating passivity or causing damage.
-
Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with Embodied Agents as Case Study
A governed upgrade framework with interface, policy, behavioral, and recovery checks keeps unsafe activations at zero across multi-round AI capability upgrades on a PyBullet/ROS 2 manipulation testbed while retaining task success near naive upgrades.
-
Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning
A hybrid DRL system for multi-pair crypto trading with deterministic risk shielding outperforms a heuristic baseline at 10% significance on Binance futures data.
-
Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
A survey that maps risks along the agent workflow and consolidates metrics and benchmarks for safety, robustness, privacy, and security in agentic AI.