arXiv subjects

Pengyuan Lu

Publications and source records attributed to Pengyuan Lu.

8 recordsLinked to original sources

arXiv2025

IBCL: Zero-shot Model Generation under Stability-Plasticity Trade-offs

Algorithms that balance the stability-plasticity trade-off are well studied in the Continual Learning literature. However, only a few focus on obtaining models for specified trade-off preferences. When solving the problem of continual learning under specific trade-offs (CLuST), state-of-the-art techniques leverage rehearsal-based learning, which requires retraining when a model corresponding to a new trade-off preference is requested. This is inefficient, since there potentially exists a significant number of different trade-offs, and a large number of models may be requested. As a response, we propose Imprecise Bayesian Continual Learning (IBCL), an algorithm that tackles CLuST efficiently. IBCL replaces retraining with a constant-time convex combination. Given a new task, IBCL (1) updates the knowledge base as a convex hull of model parameter distributions, and (2) generates one Pareto-optimal model per given trade-off via convex combination without additional training. That is, obtaining models corresponding to specified trade-offs via IBCL is zero-shot. Experiments whose baselines are current CLuST algorithms show that IBCL improves classification by at most 44% on average per task accuracy, and by 45% on peak per task accuracy while maintaining a near-zero to positive backward transfer, with memory overheads converging to constants. In addition, its training overhead, measured by the number of batch updates, remains constant at every task, regardless of the number of preferences requested. IBCL also improves multi-objective reinforcement learning tasks by maintaining the same Pareto front hypervolume, while significantly reducing the training cost. Details can be found at: https://github.com/ibcl-anon/ibcl.

cs.LG↗

arXiv2025

Conservative Perception Models for Probabilistic Verification

Verifying the behaviors of autonomous systems with learned perception components is a challenging problem due to the complexity of the perception and the uncertainty of operating environments. Probabilistic model checking is a powerful tool for providing guarantees on stochastic models of systems. However, constructing model-checkable models of black-box perception components for system-level mathematical guarantees has been an enduring challenge. In this paper, we propose a method for constructing provably conservative Interval Markov Decision Process (IMDP) models of closed-loop systems with perception components. We prove that our technique results in conservative abstractions with a user-specified probability. We evaluate our approach in an automatic braking case study using both a synthetic perception component and the object detector YOLO11 in the CARLA driving simulator.

cs.FL↗

arXiv2024

Recovery from Adversarial Attacks in Cyber-physical Systems: Shallow, Deep and Exploratory Works

Cyber-physical systems (CPS) have experienced rapid growth in recent decades. However, like any other computer-based systems, malicious attacks evolve mutually, driving CPS to undesirable physical states and potentially causing catastrophes. Although the current state-of-the-art is well aware of this issue, the majority of researchers have not focused on CPS recovery, the procedure we defined as restoring a CPS's physical state back to a target condition under adversarial attacks. To call for attention on CPS recovery and identify existing efforts, we have surveyed a total of 30 relevant papers. We identify a major partition of the proposed recovery strategies: shallow recovery vs. deep recovery, where the former does not use a dedicated recovery controller while the latter does. Additionally, we surveyed exploratory research on topics that facilitate recovery. From these publications, we discuss the current state-of-the-art of CPS recovery, with respect to applications, attack type, attack surfaces and system dynamics. Then, we identify untouched sub-domains in this field and suggest possible future directions for researchers.

eess.SY↗

arXiv2024

Repairing Learning-Enabled Controllers While Preserving What Works

Learning-enabled controllers have been adopted in various cyber-physical systems (CPS). When a learning-enabled controller fails to accomplish its task from a set of initial states, researchers leverage repair algorithms to fine-tune the controller's parameters. However, existing repair techniques do not preserve previously correct behaviors. Specifically, when modifying the parameters to repair trajectories from a subset of initial states, another subset may be compromised. Therefore, the repair may break previously correct scenarios, introducing new risks that may not be accounted for. Due to this issue, repairing the entire initial state space may be hard or even infeasible. As a response, we formulate the Repair with Preservation (RwP) problem, which calls for preserving the already-correct scenarios during repair. To tackle this problem, we design the Incremental Simulated Annealing Repair (ISAR) algorithm, which leverages simulated annealing on a barriered energy function to safeguard the already-correct initial states while repairing as many additional ones as possible. Moreover, formal verification is utilized to guarantee the repair results. Case studies on an Unmanned Underwater Vehicle (UUV) and OpenAI Gym Mountain Car (MC) show that ISAR not only preserves correct behaviors from previously verified initial state regions, but also repairs 81.4% and 23.5% of broken state spaces in the two benchmarks. Moreover, the average signal temporal logic (STL) robustnesses of the ISAR repaired controllers are larger than those of the controllers repaired using baseline methods.

eess.SY↗

arXiv2023

IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning

Like generic multi-task learning, continual learning has the nature of multi-objective optimization, and therefore faces a trade-off between the performance of different tasks. That is, to optimize for the current task distribution, it may need to compromise performance on some previous tasks. This means that there exist multiple models that are Pareto-optimal at different times, each addressing a distinct task performance trade-off. Researchers have discussed how to train particular models to address specific trade-off preferences. However, existing algorithms require training overheads proportional to the number of preferences -- a large burden when there are multiple, possibly infinitely many, preferences. As a response, we propose Imprecise Bayesian Continual Learning (IBCL). Upon a new task, IBCL (1) updates a knowledge base in the form of a convex hull of model parameter distributions and (2) obtains particular models to address task trade-off preferences with zero-shot. That is, IBCL does not require any additional training overhead to generate preference-addressing models from its knowledge base. We show that models obtained by IBCL have guarantees in identifying the Pareto optimal parameters. Moreover, experiments on standard image classification and NLP tasks support this guarantee. Statistically, IBCL improves average per-task accuracy by at most 23\% and peak per-task accuracy by at most 15\% with respect to the baseline methods, with steadily near-zero or positive backward transfer. Most importantly, IBCL significantly reduces the training overhead from training 1 model per preference to at most 3 models for all preferences.

cs.LG↗

arXiv2023

Causal Repair of Learning-enabled Cyber-physical Systems

Models of actual causality leverage domain knowledge to generate convincing diagnoses of events that caused an outcome. It is promising to apply these models to diagnose and repair run-time property violations in cyber-physical systems (CPS) with learning-enabled components (LEC). However, given the high diversity and complexity of LECs, it is challenging to encode domain knowledge (e.g., the CPS dynamics) in a scalable actual causality model that could generate useful repair suggestions. In this paper, we focus causal diagnosis on the input/output behaviors of LECs. Specifically, we aim to identify which subset of I/O behaviors of the LEC is an actual cause for a property violation. An important by-product is a counterfactual version of the LEC that repairs the run-time property by fixing the identified problematic behaviors. Based on this insights, we design a two-step diagnostic pipeline: (1) construct and Halpern-Pearl causality model that reflects the dependency of property outcome on the component's I/O behaviors, and (2) perform a search for an actual cause and corresponding repair on the model. We prove that our pipeline has the following guarantee: if an actual cause is found, the system is guaranteed to be repaired; otherwise, we have high probabilistic confidence that the LEC under analysis did not cause the property violation. We demonstrate that our approach successfully repairs learned controllers on a standard OpenAI Gym benchmark.

eess.SY↗

arXiv2023

Fulfilling Formal Specifications ASAP by Model-free Reinforcement Learning

We propose a model-free reinforcement learning solution, namely the ASAP-Phi framework, to encourage an agent to fulfill a formal specification ASAP. The framework leverages a piece-wise reward function that assigns quantitative semantic reward to traces not satisfying the specification, and a high constant reward to the remaining. Then, it trains an agent with an actor-critic-based algorithm, such as soft actor-critic (SAC), or deep deterministic policy gradient (DDPG). Moreover, we prove that ASAP-Phi produces policies that prioritize fulfilling a specification ASAP. Extensive experiments are run, including ablation studies, on state-of-the-art benchmarks. Results show that our framework succeeds in finding sufficiently fast trajectories for up to 97\% test cases and defeats baselines.

cs.LG↗

arXiv2022

Confidence Composition for Monitors of Verification Assumptions

Closed-loop verification of cyber-physical systems with neural network controllers offers strong safety guarantees under certain assumptions. It is, however, difficult to determine whether these guarantees apply at run time because verification assumptions may be violated. To predict safety violations in a verified system, we propose a three-step confidence composition (CoCo) framework for monitoring verification assumptions. First, we represent the sufficient condition for verified safety with a propositional logical formula over assumptions. Second, we build calibrated confidence monitors that evaluate the probability that each assumption holds. Third, we obtain the confidence in the verification guarantees by composing the assumption monitors using a composition function suitable for the logical formula. Our CoCo framework provides theoretical bounds on the calibration and conservatism of compositional monitors. Two case studies show that compositional monitors are calibrated better than their constituents and successfully predict safety violations.

cs.LO↗