3 papers
cs.CR2026
Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents
Junliang Liu, Ruoyu Li, Wenxin Tang +4
LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progressive-disclosure design expose…
cs.LG2025
Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-training
Huitong Jin, Yipeng Zhou, Quan Z. Sheng +2
Differentially Private Federated Learning (DPFL) strengthens privacy protection by perturbing model gradients with noise, though at the cost of reduced accuracy. Although prior emp…
cs.CL2024
Cerberus: Efficient Inference with Adaptive Parallel Decoding and Sequential Knowledge Enhancement
Yuxuan Liu, Wenyuan Li, Laizhong Cui +1
Large language models (LLMs) often face a bottleneck in inference speed due to their reliance on auto-regressive decoding. Recently, parallel decoding has shown significant promise…