Black Hat · August 28, 2026

Black Hat Asia 2026 | LLM-Empowered Differential Testing for the Ethereum Infrastructure

video AI Red Teaming Model Evaluation AI Engineering

Black Hat Asia 2026 | LLM-Empowered Differential Testing for the Ethereum Infrastructure video thumbnail

Why it matters

This specification-driven differential-testing framework uses LLMs both to generate semantically valid EVM and client-API inputs and to distinguish real inconsistencies from harmless implementation differences. Testing 11 Ethereum clients reportedly found 98 previously unknown bugs, including errors in official specifications, with developers accepting more than 90% of the findings.

My takeaway: Turn protocol requirements into executable cross-implementation tests, use the LLM to expand semantic coverage, and keep the final oracle deterministic and reviewable. Minimize every discrepancy to a reproducible case, separate specification ambiguity from implementation failure, and add confirmed cases to continuous regression suites.

Keep exploring

More curated notes connected through AI Red Teaming and Model Evaluation.

OpenAI News · framework

Pacing model development in an era of cyber-critical capabilities

OpenAI says preliminary evidence that Astra may meet its Critical cybersecurity threshold led it to pause frontier reinforcement-learning work for two weeks and keep its largest planned run on hold. New safeguards include stronger workload and network isolation, continuous boundary testing, token-level monitoring that escalates suspicious tool activity, and broader alignment checks for deception, reward hacking, and unauthorized access.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OpenAI News · framework

A blueprint for democratic governance of frontier AI

OpenAI proposes a three-part U.S. frontier-AI governance model: harmonize emerging state safety laws into a federal baseline, strengthen CAISI as an evaluation and standards institution, and coordinate a broader resilience program. Proposed controls include severe-risk evaluations, transparency reports, independent audits, safety-incident reporting, model-weight security, whistleblower protection, and periodic technical assessments.