5 papers
BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes
Laiqiao Qin, Tianqing Zhu, Longxiang Gao +1
Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or exte…
Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval
Linlin Wang, Tianqing Zhu, Laiqiao Qin +2
With recent breakthroughs in large language models (LLMs) for reasoning, planning, and complex task generation, artificial intelligence systems are transitioning from isolated sing…
Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs
Linlin Wang, Tianqing Zhu, Laiqiao Qin +2
In Large Language Models, Retrieval-Augmented Generation (RAG) systems can significantly enhance the performance of large language models by integrating external knowledge. However…
Machine Unlearning on Pre-trained Models by Residual Feature Alignment Using LoRA
Laiqiao Qin, Tianqing Zhu, Linlin Wang +1
Machine unlearning is an emerging technology that removes a subset of the training data from a trained model without significantly affecting the model performance on the remaining…
Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions
Laiqiao Qin, Tianqing Zhu, Wanlei Zhou +1
Federated Learning (FL) is a distributed and privacy-preserving machine learning paradigm that coordinates multiple clients to train a model while keeping the raw data localized. H…