
ZoneClaw-code
Benchmark and defense code for persistent memory attacks on OpenClaw-style computer-use agents, with memory-zoning mitigation, attack scenarios, and…

Benchmark and defense code for persistent memory attacks on OpenClaw-style computer-use agents, with memory-zoning mitigation, attack scenarios, and…

SecOpsMaesttro POC

Self-referenced local contrast for knowledge-poison detection in retrieval-augmented generation

C++ tool using libtins to craft and broadcast DHCP requests with random MACs across an IP pool, exhausting DHCP leases to demonstrate DHCP starvation…

Research code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…

The Security Toolkit for LLM Interactions

Lightweight evaluation harness for RAG poisoning defenses that builds four-condition clean/poisoned records and reports prevented targets, net…

Code and results for the QAI 2026 paper on FGSM attack transferability from simulation to IBM quantum hardware.

Research framework for detecting and removing backdoors in language models, combining feature-based anomaly detection with LoRA-based unlearning…

PyTorch reference implementation of a fast adversarial training method that prevents catastrophic overfitting via coupled objectives and an EMA-based…