8 papers
FORGE: Verification-Gated Behavioral Repair for Generative Language Models
Hsin-Ling Hsu, Min-Yu Chen, Nai-Chia Chen +3
Generative large language models (LLMs) inherit undesirable behaviors from pre-training, including demographic bias and toxic generation, that often emerge only after deployment an…
ConcoLixir: Reactive LLM Discovery Oracles for Python Concolic Testing
Dong Chen, Chih-Duo Hong, Fang Yu
Concolic testing combines concrete execution with symbolic constraint solving, but Python programs expose recurring limits. Library calls can cause symbolic variables to downgrade…
Signature filtering: a lightweight enhancement for statistical watermark detection in large language models
Chih-Duo Hong, Yen-Pang Chen, Fang Yu
Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive,…
OTTER: A Red-Teaming System for Toxicity-Evading Jailbreak Prompt Optimization
Jerry Wang, Hsin-Ling Hsu, Yi-Cheng Lai +2
Production LLMs increasingly rely on toxicity-based moderation filters as a primary defense, assuming that harmful intent correlates with toxic surface wording. We show this assump…
Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
Xin Su, Dawid Majchrowski, Fangyuan Yu +5
Large Language Model (LLM) generation remains expensive because autoregressive decoding calls the model once for each new token. Speculative decoding reduces this cost by drafting…
WARP: Guaranteed Inner-Layer Repair of NLP Transformers
Hsin-Ling Hsu, Min-Yu Chen, Nai-Chia Chen +3
Transformer-based NLP models remain vulnerable to adversarial perturbations, yet existing repair methods face a fundamental trade-off: gradient-based approaches offer flexibility b…
Influence-Guided Concolic Testing of Transformer Robustness
Chih-Duo Hong, Chih-Cheng Yang, Yu Wang +1
Concolic testing for neural networks alternates concrete execution with constraint solving to search for inputs that flip model decisions. We present a concolic tester for Transfor…
Concolic Testing on Individual Fairness of Neural Network Models
Ming-I Huang, Chih-Duo Hong, Fang Yu
This paper introduces PyFair, a formal framework for evaluating and verifying individual fairness of Deep Neural Networks (DNNs). By adapting the concolic testing tool PyCT, we gen…