
IPI-exposure-signal
Research pipeline for detecting latent indirect prompt-injection exposure signals in agentic LLMs via hidden-state probing, including trace…

Research pipeline for detecting latent indirect prompt-injection exposure signals in agentic LLMs via hidden-state probing, including trace…

Plugin for Binary Ninja that integrates local Ollama models to rename functions and variables in decompiled HLIL code, preserving privacy by keeping…

[NeurIPS 2025] An official source code for paper "GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning".

Research code for detecting and detoxifying backdoors in text-to-image diffusion models, with pipelines for Stable Diffusion v1.4, v1.5, XL, and 3…

Code for ACL 2026 (main) paper "DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation"

Research code for poisoning attacks on the PGM-index, demonstrating how to craft adversarial data to degrade learned index performance.

This project contains the source code for the CERT Basic Fuzzing Framework (BFF) and the CERT Failure Observation Engine (FOE).

Official code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing

Code for 'Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control'

Image-based Android malware detection framework tackling obfuscation and concept drift. Includes curated datasets and Python code for training…

Research code for extracting and training safety-awareness directions in multimodal LLMs to improve refusal behavior while limiting benign-task drift.

A fast universal code security scanner, written in Rust. Batteries included: supports 14 languages, TUI for triage, secrets, post-quantum audits,…

Robust audio watermarking framework embedding binary messages into magnitude spectrograms, with differentiable attack simulation, Q-Former pooling,…

A Deep Learning Approach for Password Guessing (https://arxiv.org/abs/1709.00440)

LSTM-based classifier for detecting domain generation algorithm (DGA) domains, with Keras implementations of neural network and bigram models for DNS…

A LSTM based framework for handling multiclass imbalance in DGA botnet detection

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

Reconstructs legacy Windows binaries into C source by pairing Ghidra decompiler exports with local LLMs, producing compile-checked candidates and…