9 papers
TI-StegoAlign: Channel-Guided Post-Training for Generative Text Steganography under Tokenization Inconsistency
Jiuan Zhou, Yuhao Xue, Yu Cheng +2
Generative text steganography enables LLM agents to exchange secret information through task-relevant messages. Yet most methods evaluate recovery on sender-side tokens, whereas th…
Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems
Yi Xie, Jiawei Du, Yu Cheng +2
Skills are becoming the capability layer through which LLM agents turn plans into actions, but their use introduces security risks such as data leakage, unauthorized operations, an…
TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
Yu Cheng, Yongkang Hu, Jiuan Zhou +8
Test-time evolution of agent memory represents a pivotal paradigm for advancing AGI, as it strengthens complex reasoning through experience accumulation without requiring parameter…
FGAS: Fixed Decoder Network-Based Audio Steganography with Adversarial Perturbation Generation
Jialin Yan, Yu Cheng, Zhaoxia Yin +4
The rapid development of Artificial Intelligence Generated Content (AIGC) has made high-fidelity generated audio widely available across the Internet, driving the advancement of au…
DTAMS: High-Capacity Generative Steganography via Dynamic Multi-Timestep Selection and Adaptive Deviation Mapping in Latent Diffusion
Yuhao Xue, Jiuan Zhou, Yu Cheng +1
With the rapid development of AIGC technologies, generative image steganography has attracted increasing attention due to its high imperceptibility and flexibility. However, existi…
VocBulwark: Towards Practical Generative Speech Watermarking via Additional-Parameter Injection
Weizhi Liu, Yue Li, Zhaoxia Yin
Generated speech achieves human-level naturalness but escalates security risks of misuse. However, existing watermarking methods fail to reconcile fidelity with robustness, as they…