6 citations · 8 across the 3 of their papers we have counts for
3 papers
cs.CR2026
AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
Zonghao Ying, Haozheng Wang, Jiangfan Liu +5
Large Language Model (LLM) agents are increasingly used to automate complex workflows, but integrating untrusted external data with privileged execution exposes them to severe secu…
cs.CR2024★ 2 cited
DLP: towards active defense against backdoor attacks with decoupled learning process
Zonghao Ying, Bin Wu
Deep learning models are well known to be susceptible to backdoor attack, where the attacker only needs to provide a tampered dataset on which the triggers are injected. Models tra…
cs.CR2024★ 6 cited
NBA: defensive distillation for backdoor removal via neural behavior alignment
Zonghao Ying, Bin Wu
Recently, deep neural networks have been shown to be vulnerable to backdoor attacks. A backdoor is inserted into neural networks via this attack paradigm, thus compromising the int…