MYWeb3

#Web3 #ZK

[MYWeb3 @imsuperkk]

I just published 一行程式碼缺失，千萬美元蒸發：SecondFi 錢包 Ed25519 簽名漏洞全解密 https://t.co/g4ho1qzfzX

[MYWeb3 @imsuperkk]

I just published In-depth analysis of the Coldcard hardware wallet RNG vulnerability: How a macro definition led to… https://t.co/0mVNWnuAWq

#Coldcard #blockchain #security #wallet

[MYWeb3 @imsuperkk]

I just published NIST AI Standards Evolution: A Deep Technical Analysis from a Cryptographic Perspective
https://t.co/T0pIa4SvI1

#security #ai #nist #privacy

[MYWeb3 @imsuperkk]

I just published Testing LLM Guardrails in Production: A Real‑World Harness for @martin_yeung/llm-up-guardrail

https://t.co/2m556CmRHa

#AI #LLM #Security #Privacy

[MYWeb3 @imsuperkk]

Get started in 30 seconds:
npm install @martin_yeung/llm-up-guardrail

Stop the 3 AM alerts. Protect your users.

☕ Support: https://t.co/GeCtyEVrnF

[MYWeb3 @imsuperkk]

Your AI chatbot just cost you $5,000 at 3 AM.
Prompt injection is the #1 OWASP risk—but most guardrails are Python-only or SaaS-locked.
I built a security tool alternative that actually stops scams.
Here’s how @martin_yeung/llm-up-guardrail saves your infra and sleep) 🧵👇

[MYWeb3 @imsuperkk]

How does it stack up?
• LLM Guard? no multi-turn.
• Lakera? SaaS lock-in + recurring costs.
• JailGuard? Single-threat (injection only).
@martin_yeung/llm-up-guardrail is the only TypeScript-native tool with:
✅ Scam-first design
✅ Behavioral tracking
✅ Zero vendor lock-in

[MYWeb3 @imsuperkk]

Built for the Node.js/TypeScript ecosystem:
⚡️ Zero runtime dependencies (no supply-chain bloat)
🔷 Full ESM + CJS, complete TypeScript types
🔌 Drop-in Express Middleware
🦜 LangChain-style wrapper
No external API calls required. Your data stays self-hosted and private.

[MYWeb3 @imsuperkk]

The Anti-Scam engine is the flagship, but covers OWASP Top 10:
✅ InjectionGuard (Jailbreak/DAN detection)
✅ PIIGuard (API keys, SSN, credit cards + entropy detection)
✅ ToxicityGuard (Self-harm, hate speech)
✅ URLSafetyScanner (Brand impersonation, shorteners, punycode)

[MYWeb3 @imsuperkk]

Most guardrails stop at regex. @martin_yeung/llm-up-guardrail goes 3 layers deep:
1️⃣ Pattern Matching (20+ curated EN/CH scam rules)
2️⃣ LLM Semantic Analysis (OpenAI/Anthropic for ambiguous cases)
3️⃣ Behavioral Tracking (catches scams that unfold over multiple turns)

[MYWeb3 @imsuperkk]

It’s 3 AM. You wake up to a alert.
Your shiny new AI support bot just handed out gift cards to a scammer who asked nicely.
This isn't a hypothetical. It's happening to production systems right now.
Most models don't understand social engineering. They just follow instructions.

[MYWeb3 @imsuperkk]

I just published From Injection Attacks to Scams: @martin_yeung/llm-up-guardrail Delivers Production‑Grade AI Security

https://t.co/hDDtl4ZBuf

#AI #LLM #Security #privacy #AIAgent

[MYWeb3 @imsuperkk]

I just published Beyond Data Privacy: New Privacy Risks for Large Language Models (arXiv:2509.14278, 2026) https://t.co/WlQREPrtal

[MYWeb3 @imsuperkk]

I just published DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation https://t.co/KXIKQHdJTE
#LLM #DSpark

[MYWeb3 @imsuperkk]

I just published Flock: Fast Proving for Batch Boolean Computations https://t.co/NdWV4fZ3cD

[MYWeb3 @imsuperkk]

I just published PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization https://t.co/KfYTjhugdM

[MYWeb3 @imsuperkk]

I just published Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States (Denis Peskoff, Joe… https://t.co/AccgbUsyz7

#LOCUS #law #AI

[MYWeb3 @imsuperkk]

I just published Generating synthetic data with differentially private LLM inference (Google Research, 2025) https://t.co/duF0L4ygAP

[MYWeb3 @imsuperkk]

I just published Encryption-Friendly LLM Architecture (D. Rho et al., arXiv:2410.02486) https://t.co/Op3BKnFTWH

[MYWeb3 @imsuperkk]

I just published EncryptedLLM: Privacy-Preserving Large Language Model Inference via GPU-Accelerated Fully… https://t.co/lLNDki0pTW