Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vulnerable to prompt injection attacks that can hijack task objectives. Existing safety alignment methods rely on static expert trajectories or preference optimization, lim...
A general fMRI sequence prediction model, the Frequency-Filtered Attention Transformer (FFAformer), which models low-frequency variations in the frequency domain to capture long-range dependencies and incorporates FC consistency constraints to preserve brain network structure.
Chengcheng Du, Fei-Fei Zhao, Yin-Qian Sun et al.· iScience· 0 citations
ForesightSafety-SAGE is introduced, a fully automated scenario generation and safety evaluation framework for LLM agents that demonstrates the importance of executable, process-level evaluation for understanding and improving LLM agent safety.
Lu Jia, Haibo Tong, Feifei Zhao et al.· 0 citations
This work proposes Wrapper-Based Intent-Form Augmentation (WIFA), an automatic intent-group augmentation method that pairs wrapped harmful examples with structurally matched wrapped benign counterexamples, requiring no external teacher or manual per-wrapper intent labels.
Ping Wu, Haibo Tong, Fei-Fei Zhao et al.· 0 citations
ForesightSafety-TIDE, a controlled evaluation framework that strictly pairs all-honest collaboration with controlled deception by a key evidence holder and analyzes the aggregation process through multi-stage voting, testimony adoption, and evidence-root lineage propagation, reveals both the fragility of distributed fa...
Chen Yan, Zeyang Yue, Fei-Fei Zhao et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
