12 papers
Fast and Accurate: Improving Personalized LLM Performance by Semantic Concentration Inspired Workload Split between RAG and Fine-Tuning
Xingke Yang, Sicong Li, Lingfeng Yao +4
With ever increasing personalized large language model (LLM) services, the next question to answer is how to improve the quality of services/users' experiences, which is indicated…
Mind Your Own Role: Reducing Role Overstepping for Effective and Efficient Multi-Agent Collaboration via Dynamic Role Activation Steering
Xingke Yang, Sicong Li, Lingfeng Yao +5
Multi-Agent Systems (MAS) have shown strong capability in solving complex tasks by assigning different agents specialized roles and corresponding subtasks. However, agents may over…
A Novel Semantic Manifold Alignment Attack against Embedding-to-Embedding Obfuscation in Privacy-Preserving LLMs
Sicong Li, Lingfeng Yao, Xingke Yang +7
With the widespread applications of large language models (LLMs), privacy-preserving inference has become increasingly essential for sensitive queries. To balance privacy and utili…
PhysWave: Physics-Guided Latent Diffusion Models for Controllable Spatial Audio Generation
Lingfeng Yao, Chenpei Huang, Xingke Yang +5
Text-to-spatial audio generation, such as text-to-First-Order Ambisonics (FOA), provides a convenient way to create spatial audio for billion-dollar gaming and film industries. How…
Decoding in Order-Agnostic Language Models: Chain-Rule Deviation and Uniform Spreading
Lin Yao
Order-agnostic language models (OALMs), including discrete diffusion language models (dLLMs), are trained to predict masked tokens under arbitrary conditioning sets, allowing seque…
Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
Lingfeng Yao, Xincong Zhong, Chenpei Huang +6
With the rise of AI-generated audio, watermarking has become widely used for detecting misuse and protecting intellectual property. However, adversaries may try to remove these wat…
WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference
Zixun Xiong, Gaoyi Wu, Lingfeng Yao +3
Communication topology is a critical factor in the utility and safety of LLM-based multi-agent systems (LLM-MAS), making it a high-value intellectual property (IP) whose confidenti…
iSeal: Encrypted Fingerprinting for Reliable LLM Ownership Verification
Zixun Xiong, Gaoyi Wu, Qingyang Yu +5
Given the high cost of large language model (LLM) training from scratch, safeguarding LLM intellectual property (IP) has become increasingly crucial. As the standard paradigm for I…
EchoMark: Perceptual Acoustic Environment Transfer with Watermark-Embedded Room Impulse Response
Chenpei Huang, Lingfeng Yao, Kyu In Lee +3
Acoustic Environment Matching (AEM) is the task of transferring clean audio into a target acoustic environment, enabling engaging applications such as audio dubbing and auditory im…
Who's Wearing? Ear Canal Biometric Key Extraction for User Authentication on Wireless Earbuds
Chenpei Huang, Lingfeng Yao, Hui Zhong +5
Ear canal scanning/sensing (ECS) has emerged as a novel biometric authentication method for mobile devices paired with wireless earbuds. Existing studies have demonstrated the uniq…
Yours or Mine? Overwriting Attacks Against Neural Audio Watermarking
Lingfeng Yao, Chenpei Huang, Shengyao Wang +6
As generative audio models are rapidly evolving, AI-generated audios increasingly raise concerns about copyright infringement and misinformation spread. Audio watermarking, as a pr…
SpeechVerifier: Robust Acoustic Fingerprint against Tampering Attacks via Watermarking
Lingfeng Yao, Chenpei Huang, Shengyao Wang +5
With the surge of social media, maliciously tampered public speeches, especially those from influential figures, have seriously affected social stability and public trust. Existing…