Jul 2026
Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components
GradLock is introduced, a novel training-time injection attack that stealthily injects sensitive training data directly into the model parameters and employs dynamic gradient locking to prevent payload degradation during the optimization process.
Jin-Seong Kim, Han-Ju Lee, Seok-Won Hong et al.
· arXiv.org · 0 citations