6 papers
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…
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…
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…
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…
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…