
SecOPD
Research implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith,…

Research implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith,…

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

Standardized adversarial robustness benchmark with a public leaderboard and downloadable model zoo for evaluating ML models against Lp attacks and…

Interpretability and explainability of data and machine learning models

A curated list of useful resources that cover Offensive AI.

Clusters and elements to attach to MISP events or attributes (like threat actors)

Interactive dashboards and libraries for responsible AI model debugging, covering error analysis, fairness, interpretability, counterfactuals, causal…

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in…

Proof-of-concept exploit for CVE-2026-73292: CSRF attack on Semaphore UI password change endpoint, serving a malicious page that silently resets an…

A curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.

Research-only AI watermark robustness toolkit: local reverse proxy strips C2PA/EXIF/XMP, Unicode, image/audio stego, OOXML/PDF metadata, and scans…

Different methods to detect a virtualized environment or potential debugging

A curated collection of resources for learning and researching LLM prompt injection attacks, defenses, and security.

A font-based deception tool for red teaming, security research, and whatever else.

CVE-2026-20685 - Draft or TODO

During the exploitation phase of a pen test or ethical hacking engagement, you will ultimately need to try to cause code to run on target system…

Tools and PoCs for Windows syscall investigation.