3 papers
cs.AI2026
MIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information Bottleneck
Dongyi Liu, Haixing He, Xiaobao Wu +1
Memory-augmented LLM-based agents are vulnerable to memory injection attacks: Agents may retrieve poisoned memory from attackers, which diverts their behavior from initial user int…
cs.CR2025
Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers
Dongyi Liu, Jiangtong Li
Graph Neural Networks(GNNs) are vulnerable to backdoor attacks, where adversaries implant malicious triggers to manipulate model predictions. Existing trigger generators are often…
cs.CR2024
Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool
Jiangtong Li, Dungy Liu, Dawei Cheng +1
\textbf{G}raph \textbf{N}eural \textbf{N}etworks~(GNNs) have achieved significant success in various real-world applications, including social networks, finance systems, and traffi…