1 citations · 1 across the 10 of their papers we have counts for
10 papers
E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
Zhisheng Zhang, Derui Wang, Yifan Mi +6
Recent advancements in speech synthesis technology have enriched our daily lives, with high-quality and human-like audio widely adopted across real-world applications. However, mal…
ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models
Weifei Jin, Yuxin Cao, Junjie Su +5
Recent advances in Audio-Language Models (ALMs) have significantly improved multimodal understanding capabilities. However, the introduction of the audio modality also brings new a…
Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
Haodong Lu, Chongyang Zhao, Minhui Xue +3
Continual learning (CL) with large pre-trained models aims to incrementally acquire knowledge without catastrophic forgetting. Existing LoRA-based Mixture-of-Experts (MoE) methods…
Continual Learning on CLIP via Incremental Prompt Tuning with Intrinsic Textual Anchors
Haodong Lu, Xinyu Zhang, Kristen Moore +4
Continual learning (CL) enables deep networks to acquire new knowledge while avoiding catastrophic forgetting. The powerful generalization ability of pre-trained models (PTMs), suc…
Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems
Weifei Jin, Yuxin Cao, Junjie Su +6
The widespread application of automatic speech recognition (ASR) supports large-scale voice surveillance, raising concerns about privacy among users. In this paper, we concentrate…
CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization
Derui Wang, Kristen Moore, Diksha Goel +8
Deep reinforcement learning (DRL) has gained widespread adoption in control and decision-making tasks due to its strong performance in dynamic environments. However, DRL agents are…
Bones of Contention: Exploring Query-Efficient Attacks against Skeleton Recognition Systems
Yuxin Cao, Kai Ye, Derui Wang +4
Skeleton action recognition models have secured more attention than video-based ones in various applications due to privacy preservation and lower storage requirements. Skeleton da…
Take Only What You Need: Rank Minimization as an Implicit Forgetting Regularizer in Continual Learning
Haodong Lu, Chongyang Zhao, Minhui Xue +3
The central tension in continual learning (CL) is the trade-off between plasticity (acquiring new knowledge) and stability (retaining prior knowledge). We study how a pre-trained b…
QUEEN: Query Unlearning against Model Extraction
Huajie Chen, Tianqing Zhu, Lefeng Zhang +4
Model extraction attacks currently pose a non-negligible threat to the security and privacy of deep learning models. By querying the model with a small dataset and usingthe query r…
Provably Unlearnable Data Examples
Derui Wang, Minhui Xue, Bo Li +2
The exploitation of publicly accessible data has led to escalating concerns regarding data privacy and intellectual property (IP) breaches in the age of artificial intelligence. To…