
bitcoder-v2-research
Research repository documenting LLM generalization ceilings in code security vulnerability detection, with cross-evaluation across synthetic and…

Research repository documenting LLM generalization ceilings in code security vulnerability detection, with cross-evaluation across synthetic and…

Analyzes LLM internal states and 100+ attention/probability features to train classifiers that detect document poisoning attacks in RAG systems.

Hide valuable information where it's least expected

CLPSTNet: A Progressive Multi-Scale Convolutional Steganography Model Integrating Curriculum Learning

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

A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.

Prohibited Items Segmentation via Occlusion-aware Bilayer Modeling (ICME 2025)

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…

Public version of the Entropica repo

détection des attaques sql/xss sur API web avec IA

AGLS

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

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

Extracts structured Cyber Threat Intelligence (CTI) from PDF, DOCX, and TXT documents using LLMs. Generates MITRE ATT&CK attack flows, detection…

This repository hosts a multimodal web attack dataset (MWAD) to advance AI-driven threat detection research.

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

Open standard for documenting security-relevant metadata of AI models, including training data provenance, PII risk, known vulnerabilities, and…

This repository includes the source code used in the "Characterization and Detection of Cross-Router Covert Channels" paper.