Search papers, labs, and topics across Lattice.
Affiliation:
2
0
5
10
LLMs can dramatically improve taint analysis for Android apps, achieving an F1-score of 0.96 compared to traditional tools' 0.55.
Code LLMs don't just memorize training data – some generalize far better than others, and even "leaky" datasets like CVEFixes show surprisingly low memorization advantage.
