Trusted-System-Lab
Popular repositories Loading
Repositories
- GHOST Public
Official repo for the paper "Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation" in Asia CCS 2026.
- ClieND Public
Repo for "ClieND: Client-Side Neuron-Level Detection against Poisoning Attacks on Cross-Silo Federated Learning" in Asia CCS'26.
- WraAct Public
WraAct is an artifact for the paper "Convex Hull Approximation for Activation Functions" (OOPSLA'25), which provides a sound but incomplete neural network verifiers by over-approximating the function hulls of various activation functions (including leaky ReLU, ReLU, sigmoid, tanh, and maxpool).
- ReTrace Public
Repo for "ReTrace: Reinforcement Learning-Guided Reconstruction Attacks on Machine Unlearning" in ICLR'26.
- model-specificity Public
- WraLU Public
WraLU is an artifact for the paper "ReLU Hull Approximation" (POPL'24), which provides a sound but incomplete neural network verifier by over-approximating ReLU function hull.
- PdD Public
PdD is an artifact for the paper "Formalizing Robustness Against Character-Level Perturbations for Neural Network Language Models" (ICFEM'23), which provides a tool for adversarial training by generating character-level perturbation
- UQ-Trust-Lab.github.io Public
People
This organization has no public members. You must be a member to see who’s a part of this organization.
Top languages
Loading…
Most used topics
Loading…