y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#code-auditing News & Analysis

4 articles tagged with #code-auditing. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles
AI × CryptoBullisharXiv – CS AI · Jun 57/10
🤖

AttackPathGNN: Cross-function vulnerability detection in smart contracts using state interference graphs and conjunction pooling

Researchers introduce AttackPathGNN, a graph neural network that detects smart contract vulnerabilities by analyzing relationships between functions rather than isolated code patterns. The method achieves 92.3% F1 score on test datasets and identifies exploits like reentrancy that existing detectors miss, addressing security gaps exposed by historical attacks like The DAO.

AIBearisharXiv – CS AI · Apr 207/10
🧠

ASMR-Bench: Auditing for Sabotage in ML Research

Researchers introduced ASMR-Bench, a benchmark for detecting sabotage in ML research codebases, revealing that current frontier LLMs and human auditors struggle to identify subtle implementation flaws that produce misleading results. The study found even the best-performing model (Gemini 3.1 Pro) achieved only 77% AUROC and 42% fix rate, highlighting critical vulnerabilities in AI-assisted research validation.

🧠 Gemini
CryptoBullishVitalik Buterin Blog · May 186/10
⛓️

A shallow dive into formal verification

This article provides an introductory overview of formal verification, a mathematical approach to proving software correctness that has become increasingly important in cryptocurrency and blockchain development. The piece examines how formal verification methods can enhance security and reliability in smart contracts and critical systems.

AINeutralarXiv – CS AI · Mar 96/10
🧠

ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code

Researchers have developed ESAA-Security, a new architecture for conducting secure, verifiable audits of AI-generated code using structured agent workflows rather than unstructured LLM conversations. The system creates an immutable audit trail through event-sourcing and produces comprehensive security reports across 26 tasks and 95 executable checks.