Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
- adversarial-attacks
- ai-safety
- autonomous-driving
- backdoor-attacks
105,102 visible repositories in the index
529–552 of 595 · Most stars
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses | 500+ Papers | Perception, Cognition, Planning, Interaction, Agentic System
Official implementation of "AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers"
TransformerCPI: Improving compound–protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments(BIOINFORMATICS 2020) https://doi.org/10.1093/bioinformatics/btaa524
A dual-agent framework leveraging left-brain logic (structured coding, syntax validation, debugging) and right-brain intuition (macro architecture, creative patterns, UX flows). It splits cognitive loads to boost LLM development efficiency, preventing hallucination while maximizing system scalability.
Interpretable bilinear attention network with domain adaptation improves drug-target prediction.
Hierarchical Attentive Recurrent Tracking
unXOR will search a XORed file and try to guess the key using known-plaintext attacks.
A simple script which implements different Cognito attacks such as Account Oracle or Priviledge Escalation
A native Windows tray app for laptop power, battery runtime and background CPU activity. CPU RAPL, GPU NVML, battery WMI. AC total is a labelled CPU+GPU dual-load sum.
A CLI tool to automatically add type annotations into Python code. Must have tool for annotating existing code.
Stoik-Stitch-Creator: Windows Cross-Stitch Pattern Design Tool with Image Conversion and Canvas Cont
Toolbox for the analysis of smFISH images.
A graph reliability toolbox based on PyTorch and PyTorch Geometric (PyG).
TensorFlow implementation of the paper "Hierarchical Attention Networks for Document Classification"
Simple Google Maps address formatter for Wagtail fields
brute force SSH public-key authentication
A Tensorfflow implementation of Attend, Infer, Repeat
ThreatTracker is a Python script designed to monitor and generate alerts on given sets of indicators of compromise (IOCs) indexed by a set of Google Custom Search Engines.
This project is designed to create deceptive webpages to deceive and redirect attackers away from real websites.
YALIH (Yet Another Low Interaction Honeyclient) is a low Interaction Client honeypot designed to detect malicious websites through signature, anomaly and pattern matching techniques
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
The Intelligent Honey Net Project attempts to create actionable information from honeypots
Find which of your direct GitHub dependencies is susceptible to RepoJacking attacks
AI crypto trading bot with deep neural network (84.9% accuracy, 25 coins). BiLSTM + Attention trained on GPU. Bybit, Binance, OKX, Gate.io. Free cloud or self-hosted.