Hacking, PenTest, and Cybersecurity Tools for Your Security Arsenal!
Backdoor-Attack-Defense-LLMs — Research code implementing backdoor attack and defense methods for LLMs, including IBSD, SLIP, BeDKD, and BadApex algorithms. | Kitploit
The IBSD is the code of the published paper "IBSD: Iterable Black-box Self-defense Against Backdoor Attacks" on the IEEE Signal Processing Letters (2025.10)paper link
The SLIP is the code of the published paper "SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs" on the 2026-ACL-findings paper link.
The BeDKD is the code of the accepted paper "BeDKD: Backdoor Defense based on Directional Mapping Module and Adversarial Knowledge Distillation" on the 2026-AAAI paper link.
The BadApex is the code of the preprint paper "BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models" on the ArXiv paper link
cau-iss-lab/backdoor-attack-defense-llms
