.png&w=256&q=75)
🤝 Top Collaborators
.png&w=640&q=75)
🤓 Latest Submissions
SafeScreen AI
SafeScreen AI is designed as a local first line of defense. It runs directly on a Snapdragon-powered Android device using ExecuTorch and analyzes visual content on-device in real time. When the system detects potentially explicit, abusive, or manipulated media, it can immediately warn, blur, redact, mask, or block the content directly on screen before the user fully engages with it. Our initial focus is on two high-impact use cases: 1. Real-time explicit and harmful visual content protection, especially for young kids, teens, and women who may be targeted by unsafe content, online abuse, harassment, impersonation, or AI-generated explicit media. Many vulnerable users may not have the technical awareness to recognize manipulated or harmful content before it affects them. SafeScreen AI acts as a private safety shield that can blur or redact harmful content in the moment, reducing exposure before harm spreads. 2. Deepfake and manipulated media detection, helping users recognize synthetic or altered images and videos before trusting, sharing, or being harmed by them. This matters because AI-generated abuse is no longer hypothetical. Recent reporting has found AI-generated explicit deepfakes spreading in schools and affecting hundreds of students globally. Research on publicly available deepfake model variants found nearly 35,000 downloadable deepfake-related models, with almost 15 million downloads since late 2022; 96% of the targeted individuals were women. Online harm is also increasingly recognized by governments and advocacy groups as a serious form of non-consensual intimate image abuse. Using ExecuTorch and Snapdragon acceleration, we aim to build a low-latency, privacy-preserving pipeline that captures visual input, runs lightweight models locally, and responds immediately with protective actions such as warning, blurring, redaction, masking, or blocking.
28 Jun 2026
ARIA - A Fully Trustless Agent with ERC-8004
ARIA (Autonomous Risk-Intelligence Agent) is a production-grade multi-strategy AI trading agent that executes via Kraken CLI, enforces 13 risk-adjusted gates with Kelly Criterion sizing, optimizes DeFi yield, and makes every decision cryptographically verifiable on-chain via ERC-8004 on Ethereum Sepolia. ARIA runs three parallel strategies on a shared Kraken paper account: - Quant Trader (75% budget) — Grok 4.2 reasoning over 13 technical indicators with composite signal scoring and Kelly Criterion sizing. Every trade passes 13 mandatory risk gates. - Stablecoin Arbitrage (25% budget) — 5 sub-strategies at 1-second intervals: peg snap-back, cross-stable relative value, triangular arb, flash crash sniper, and orderbook imbalance across USDT/USDC/DAI/USDE. - Yield Optimizer — Analyzes Aerodrome LP pools on Base for optimal risk-adjusted yield allocation. Every decision — BUY, SELL, or HOLD — passes through a 12-step verifiable pipeline: market scan, AI reasoning via Grok 4.2, 13 mandatory risk gates, on-chain validation through ARIAValidatorV4 (8 Solidity gates), Kelly sizing, Kraken execution, EIP-712 signed checkpoints, IPFS rationale upload, RiskRouter trade intent on Sepolia, ValidationRegistry attestation, TEE tamper-proof proof, and ReputationRegistry feedback. Rejected trades are logged on-chain via RejectionLogger — proving the risk engine blocks bad trades, not just good ones. 9,200+ on-chain transactions | 1,200+ attestations | 99/100 trust score | 500+ trade intents | Zero risk gate bypasses.
12 Apr 2026
