#1Adversarial ML attack frameworks, evasion techniques, and model robustness evaluation tools.
Kitploit recommended

RunAs Utility Credential Stealer implementing 3 techniques : Hooking CreateProcessWithLogonW, Smart Keylogging, Remote Debugging
I Know Where Your Page Lives: Derandomizing the latest Windows 10 Kernel - ZeroNights 2016

Exploits the Windows Server 2025 dMSA privilege escalation vulnerability to enumerate writable OUs, escalate to arbitrary domain users, extract…

Port of Cobalt Strike's Process Inject Kit

Data from a BRAWL Automated Adversary Emulation Exercise

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

Lockbit3.0 Microsoft Defender MpClient.dll DLL Hijacking PoC

Anti-LLM obfuscation via finger counting

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

Evolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…

Delving into the Realm of LLM Security: An Exploration of Offensive and Defensive Tools, Unveiling Their Present Capabilities.

This novel way of using NtQueueApcThreadEx by abusing the ApcRoutine and SystemArgument[0-3] parameters by passing a random pop r32; ret gadget can…

Playbook-based adversary simulation framework that compiles JSON-defined attack paths into position-independent shellcode payloads for validating…

A tool to find folders excluded from AV real-time scanning using a time oracle

CobaltWhispers is an aggressor script that utilizes a collection of Beacon Object Files (BOF) for Cobalt Strike to perform process injection,…

A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

Jormungandr is a kernel implementation of a COFF loader, allowing kernel developers to load and execute their COFFs in the kernel.

Collection of VBA macro published in our twitter / blog