5 papers
Alignment Defends LLMs from Property Inference Attacks
Pengrun Huang, Chhavi Yadav, Ruihan Wu +1
Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties. Recent work has shown that such dataset-l…
Dataset Watermarking for Closed LLMs with Provable Detection
Pengrun Huang, Kamalika Chaudhuri, Yu-Xiang Wang
Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data, raising the possibility that these models may have been trained on proprietar…
Towards Energy-Efficient and Low-Latency Voice-Controlled Smart Homes: A Proposal for Offline Speech Recognition and IoT Integration
Peng Huang, Imdad Ullah, Xiaotong Wei +3
The smart home systems, based on AI speech recognition and IoT technology, enable people to control devices through verbal commands and make people's lives more efficient. However,…
ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features
Peng Cheng, Yuwei Wang, Peng Huang +5
Extensive research has revealed that adversarial examples (AE) pose a significant threat to voice-controllable smart devices. Recent studies have proposed black-box adversarial att…
Phoneme-Based Proactive Anti-Eavesdropping with Controlled Recording Privilege
Peng Huang, Yao Wei, Peng Cheng +5
The widespread smart devices raise people's concerns of being eavesdropped on. To enhance voice privacy, recent studies exploit the nonlinearity in microphone to jam audio recorder…