Wagner Research Group

diversevul

DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection (RAID 2023) https://surrealyz.github.io/files/pubs/raid23-diversevul.pdf

active-learning

Continuous Learning for Android Malware Detection (USENIX Security 2023)

MarkMyWords

reap-benchmark

REAP: A Large-Scale Realistic Adversarial Patch Benchmark

prompt-injection-defense

Fine-tuning base models to build robust task-specific models

demystify-random-transform

geoadex

GeoAdEx: A geometric approach for finding minimum-norm adversarial examples on k-NN classifiers

pubdef

Official code for "PubDef: Defending Against Transfer Attacks From Public Models" (ICLR 2024)

robust-self-attention

ssh_keystroke_analytics

dual-domain-at

Improving the Accuracy-Robustness Trade-Off for Dual-Domain Adversarial Training

.github

wagner-group.github.io

Lab website