
VehApiResolve
Resolves Windows APIs at runtime using vectored exception handlers and hashed lookups to hide imports and slow reverse engineering of offensive…

Resolves Windows APIs at runtime using vectored exception handlers and hashed lookups to hide imports and slow reverse engineering of offensive…

a small wiper malware programmed in c#

Modular LLM vulnerability scanner that probes for hallucination, data leakage, prompt injection, jailbreaks, and toxicity using static, dynamic, and…

Threadless Process Injection using remote function hooking.

A tool for generating .NET serialized gadgets that can trigger .NET assembly load/execution when deserialized using BinaryFormatter from JS/VBS/VBA…

Inject DLLs into the explorer process using icons

Research implementation of an LLM jailbreak agent that bypasses commercial model guardrails using harmless prompt weaving and adaptive tree search.

Hides reflective payloads in GPU memory via CUDA APIs, wiping host memory during sleep and using a VEH handler to restore executable memory, evading…

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

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

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

PoC for Windows privilege escalation and code injection using OfficeClickToRun RPC and undocumented shim manipulation to inject DLLs into SYSTEM…

Windows privilege-escalation exploit abusing SeImpersonate via DiagTrack RPC, using Secondary Logon to get an INTERACTIVE token and gain SYSTEM.

Agentic jailbreak framework for LLM-based agents using scheme-based task decomposition, multi-turn disguising strategies, and adaptive self-evolution…

Demonstrates using machine learning to predict random number generator sequences, highlighting cryptographic weaknesses through adversarial analysis.

Attack framework for breaking fine-tuning based prompt injection defenses (SecAlign, SecAlign++, StruQ) using architecture-aware adversarial attacks…

Defense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…

LLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…