y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#bug-detection News & Analysis

7 articles tagged with #bug-detection. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

7 articles
AI × CryptoBearishCoinDesk · Jun 57/10
🤖

AI exposed a massive flaw in top crypto network and experts warn banks could be next

An AI model discovered a critical vulnerability in Zcash that persisted undetected for four years, prompting security researchers to warn that similar hidden flaws likely exist across cryptocurrency networks and traditional financial systems. The incident highlights both AI's value in identifying security threats and the broader vulnerability landscape in digital finance infrastructure.

AI exposed a massive flaw in top crypto network and experts warn banks could be next
AI × CryptoNeutralarXiv – CS AI · May 297/10
🤖

Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agents

Researchers introduced Agora, a multi-agent LLM framework designed to detect deep logic bugs in consensus protocols used by blockchains and distributed systems. The system discovered 15 previously unknown protocol-level bugs in major implementations (Raft, EPaxos, HotStuff, BullShark) that existing LLM approaches failed to identify, demonstrating the effectiveness of domain-aware collaborative AI for protocol verification.

AIBullisharXiv – CS AI · Mar 277/10
🧠

Model2Kernel: Model-Aware Symbolic Execution For Safe CUDA Kernels

Researchers developed Model2Kernel, a system that automatically detects memory safety bugs in CUDA kernels used for large language model inference. The system discovered 353 previously unknown bugs across popular platforms like vLLM and Hugging Face with only nine false positives.

🏢 Hugging Face
AINeutralarXiv – CS AI · Apr 66/10
🧠

GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers

Researchers introduced GBQA, a new benchmark with 30 games and 124 verified bugs to test whether large language models can autonomously discover software bugs. The best-performing model, Claude-4.6-Opus, only identified 48.39% of bugs, highlighting the significant challenges in autonomous bug detection.

🧠 Claude