3 papers
cs.IT2025
New Second-Order Achievability Bounds for Coding with Side Information via Type Deviation Convergence
Xiang Li, Cheuk Ting Li
We propose a framework for second-order achievability, called type deviation convergence, that is generally applicable to settings in network information theory, and is especially…
cs.LG2024
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
Kai Hu, Weichen Yu, Yining Li +7
Recent research indicates that large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content. This paper introduces a novel token-level att…
cs.CV2024
Null Space Properties of Neural Networks with Applications to Image Steganography
Xiang Li, Kevin M. Short
This paper explores the null space properties of neural networks. We extend the null space definition from linear to nonlinear maps and discuss the presence of a null space in neur…