25 citations · 97 across the 30 of their papers we have counts for
31 papers
SPK: Eliciting Structured Prior Knowledge for Interpretable Out-of-Distribution Detection in Real-Time Object Detection
Changshun Wu, Weicheng He, Xiaowei Huang +1
Object detectors often produce over-confident predictions for objects outside their training categories, leading to so-called out-of-distribution (OoD) hallucinations. Existing app…
Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment
S. Bensalem, Y. Dong, M. Franzle +6
This position paper argues that enforcing LLM agent safety within a single abstraction layer is not merely suboptimal but categorically insufficient for deployed LLM agents -- a st…
Bridging Language Models and Formal Methods for Intent-Driven Optical Network Design
Anis Bekri, Amar Abane, Abdella Battou +1
Intent-Based Networking (IBN) aims to simplify network management by enabling users to specify high-level goals that drive automated network design and configuration. However, tran…
Randomized Smoothing Meets Vision-Language Models
Emmanouil Seferis, Changshun Wu, Stefanos Kollias +2
Randomized smoothing (RS) is one of the prominent techniques to ensure the correctness of machine learning models, where point-wise robustness certificates can be derived analytica…
LoRA-BAM: Input Filtering for Fine-tuned LLMs via Boxed Abstraction Monitors over LoRA Layers
Changshun Wu, Tianyi Duan, Saddek Bensalem +1
Fine-tuning large language models (LLMs) improves performance on domain-specific tasks but can lead to overfitting, making them unreliable on out-of-distribution (OoD) queries. We…
Revisiting Out-of-Distribution Detection in Real-time Object Detection: From Benchmark Pitfalls to a New Mitigation Paradigm
Changshun Wu, Weicheng He, Chih-Hong Cheng +2
Out-of-distribution (OoD) inputs pose a persistent challenge to deep learning models, often triggering overconfident predictions on non-target objects. While prior work has primari…
Safeguarding Large Language Models: A Survey
Yi Dong, Ronghui Mu, Yanghao Zhang +9
In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure t…
Runtime Monitoring and Enforcement of Conditional Fairness in Generative AIs
Chih-Hong Cheng, Changshun Wu, Xingyu Zhao +2
The deployment of generative AI (GenAI) models raises significant fairness concerns, addressed in this paper through novel characterization and enforcement techniques specific to G…
BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection
Changshun Wu, Weicheng He, Chih-Hong Cheng +2
Out-of-distribution (OoD) detection techniques for deep neural networks (DNNs) become crucial thanks to their filtering of abnormal inputs, especially when DNNs are used in safety-…
A Digital Twin prototype for traffic sign recognition of a learning-enabled autonomous vehicle
Mohamed AbdElSalam, Loai Ali, Saddek Bensalem +6
In this paper, we present a novel digital twin prototype for a learning-enabled self-driving vehicle. The primary objective of this digital twin is to perform traffic sign recognit…
What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems
Saddek Bensalem, Chih-Hong Cheng, Wei Huang +3
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it…
Towards Rigorous Design of OoD Detectors
Chih-Hong Cheng, Changshun Wu, Harald Ruess +1
Out-of-distribution (OoD) detection techniques are instrumental for safety-related neural networks. We are arguing, however, that current performance-oriented OoD detection techniq…
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation
Xiaowei Huang, Wenjie Ruan, Wei Huang +14
Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many…
Prioritizing Corners in OoD Detectors via Symbolic String Manipulation
Chih-Hong Cheng, Changshun Wu, Emmanouil Seferis +1
For safety assurance of deep neural networks (DNNs), out-of-distribution (OoD) monitoring techniques are essential as they filter spurious input that is distant from the training d…
Customizable Reference Runtime Monitoring of Neural Networks using Resolution Boxes
Changshun Wu, Yliès Falcone, Saddek Bensalem
Classification neural networks fail to detect inputs that do not fall inside the classes they have been trained for. Runtime monitoring techniques on the neuron activation pattern…
Institution-based Encoding and Verification of Simple UML State Machines in CASL/SPASS
Tobias Rosenberger, Saddek Bensalem, Alexander Knapp +1
This paper provides the first correct semantical representation of UML state-machines within the logical framework of an institution (previous attempts were flawed). A novel encodi…
Performance Evaluation of the NDN Data Plane Using Statistical Model Checking
Siham Khoussi, Ayoub Nouri, Junxiao Shi +4
Named Data Networking (NDN) is an emerging technology for a future internet architecture that addresses weaknesses of the Internet Protocol (IP). Since Internet users and applicati…
Proceedings of the 1st International Workshop on Methods and Tools for Rigorous System Design
Simon Bliudze, Saddek Bensalem
This volume contains the proceedings of the 1st International Workshop on Methods and Tools for Rigorous System Design (MeTRiD 2018), held on the 15th of April, 2018 in Thessalonik…
Left-eigenvectors are certificates of the Orbit Problem
Steven de Oliveira, Virgile Prevosto, Peter Habermehl +1
This paper investigates the connexion between the Kannan-Lipton Orbit Problem and the polynomial invariant generator algorithm PILA based on eigenvectors computation. Namely, we re…
Monitoring Distributed Component-Based Systems
Hosein Nazarpour, Yliès Falcone, Mohamad Jaber +2
This paper addresses the online monitoring of distributed component-based systems with multi-party interactions against user-provided properties expressed in linear-temporal logic…
Concurrency-Preserving and Sound Monitoring of Multi-Threaded Component-Based Systems
Hosein Nazarpour, Yliès Falcone, Saddek Bensalem +1
This paper addresses the monitoring of logic-independent linear-time user-provided properties in multi-threaded component-based systems. We consider intrinsically independent compo…
Synthesizing invariants by solving solvable loops
Steven de Oliveira, Saddek Bensalem, Virgile Prevosto
When proving invariance properties of a program, we face two problems. The first problem is related to the necessity of proving tautologies of considered assertion language, wherea…
Polynomial invariants by linear algebra
Steven de Oliveira, Saddek Bensalem, Virgile Prevosto
We present in this paper a new technique for generating polynomial invariants, divided in two independent parts : a procedure that reduces polynomial assignments composed loops ana…
Compositional Verification for Timed Systems Based on Automatic Invariant Generation
Lacramioara Astefanoaei, Souha Ben Rayana, Saddek Bensalem +2
We propose a method for compositional verification to address the state space explosion problem inherent to model-checking timed systems with a large number of components. The main…