Security

Two-Stage Backdoor Defense (TSBD) unveils and mitigates backdoor vulnerabilities by cleverly unlearning weight changes and suppressing backdoor neuron activeness, significantly improving the robustnes…

SWE-agent achieves state-of-the-art performance on software engineering benchmarks by creating a custom agent-computer interface that enhances LM agents’ ability to use computers.

KF-GVD: a novel knowledge fusion-based method boosts vulnerability detection accuracy by integrating task-specific knowledge into graph neural networks, achieving significant performance gains and dis…

Weighted reservoir sampling stabilizes online learning algorithms by creating a robust ensemble of intermediate solutions, significantly improving accuracy and mitigating sensitivity to outliers.

This research shows how to improve Stackelberg game strategies by considering side information, achieving no-regret learning in online settings with stochastic contexts or followers.

DiffuPac generates realistic adversarial network packets evading NIDS detection without requiring specific NIDS knowledge, outperforming existing methods.

A novel conjugate Bayesian two-step change point detection method for Hawkes processes, CoBay-CPD, achieves higher accuracy and efficiency by employing data augmentation for improved dynamic event mod…

BACKTIME unveils effective backdoor attacks on multivariate time series forecasting, highlighting vulnerabilities and offering novel defense strategies.