
modelaudit
Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

Curated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…

Simple (relatively) things allowing you to dig a bit deeper than usual.

Research code implementing backdoor attack and defense methods for LLMs, including IBSD, SLIP, BeDKD, and BadApex algorithms.

Weaponize DLL hijacking easily. Backdoor any function in any DLL.

Curated list of backdoor learning papers, surveys, and toolboxes, organizing poisoning-based attacks and defenses in deep learning for researchers…

Dropping a powershell script at %HOMEPATH%\Documents\WindowsPowershell\ , that contains the implant's path , and whenever powershell process is…