3 papers
cs.CL2026
When Emotion Becomes Trigger: Emotion-style dynamic Backdoor Attack Parasitising Large Language Models
Ziyu Liu, Tao Li, Tianjie Ni +5
Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token level and lack deeper semantic…
cs.LG2024
Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending against Poisoning Attacks
Ao Liu, Wenshan Li, Beibei Li +3
Recent studies have revealed the vulnerability of graph neural networks (GNNs) to adversarial poisoning attacks on node classification tasks. Current defensive methods require subs…
cs.LG2024
Graph Agent Network: Empowering Nodes with Inference Capabilities for Adversarial Resilience
Ao Liu, Wenshan Li, Tao Li +5
End-to-end training with global optimization have popularized graph neural networks (GNNs) for node classification, yet inadvertently introduced vulnerabilities to adversarial edge…