KidnapRAG
chanwoochoi316/kidnapragBlack-box attack framework that hijacks reasoning in agentic retrieval-augmented generation systems by injecting poisoned documents, with support for…
adversarial-attackai-securitymachine-learning
2
chanwoochoi316/kidnapragBlack-box attack framework that hijacks reasoning in agentic retrieval-augmented generation systems by injecting poisoned documents, with support for…
gpt-laboratory/trustworthyragAn Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Retrieval-Augmented Generation Systems.
bethgelab/foolboxA Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
jaidedai/easyocrReady-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
blue-yonder/tsfreshAutomatic extraction of relevant features from time series:
mandiant/stringsifterA machine learning tool that ranks strings based on their relevance for malware analysis.
jiep/offensive-ai-compilationA curated list of useful resources that cover Offensive AI.
promptfoo/modelauditSecurity scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment
tesseract-ocr/tesseractOpen-source OCR engine with LSTM neural network models for extracting text from images and scanned documents in 100+ languages via CLI, C/C++…
ultralytics/ultralyticsDeep learning framework for object detection, segmentation, classification, pose estimation, and tracking using pre-trained YOLO models and…
apache/spamassassinOpen-source email filtering framework that detects spam and phishing using content analysis, header checks, Bayesian scoring, and DNS blocklists.
stumpy-dev/stumpyScalable Python library for time series analysis via matrix profiles, enabling motif discovery, anomaly detection, semantic segmentation, and…
unit8co/dartsA python library for user-friendly forecasting and anomaly detection on time series.
guillaumemeyer/watermarks-removerA privacy-first app that strips AI watermarks from content you own.
yingtaoren/d-scanAnalyzes LLM internal states and 100+ attention/probability features to train classifiers that detect document poisoning attacks in RAG systems.
ryehr/hitms_steganographyEmbed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…
ghostpack/deeppassHunting for passwords with deep learning
ahaggard2013/binaryninja-ollamaPlugin for Binary Ninja that integrates local Ollama models to rename functions and variables in decompiled HLIL code, preserving privacy by keeping…