Yige Li

BackdoorLLM. [NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models

NAD. This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://openreview.net/pdf?id=9l0K4OM-oXE) in PyTorch.

ABL. Anti-Backdoor learning (NeurIPS 2021)

RNP. Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)

Multi-Trigger-Backdoor-Attacks. [IEEE TDSC] Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks

Ensemble_CNN_Models_For_Classification. Ensemble_CNN _Models_For_Classification.

Expose-Before-You-Defend. Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models

AutoBackdoor. “AI model poisoning industry” (highlighted in the 315 consumer protection program) shows that manipulating AI outputs via crafted content is no longer theoretical.

backdoorllm-website.github.io. JavaScript