🧠 AI🔴 Bearish

ZeroDayBench: Evaluating LLM Agents on Unseen Zero-Day Vulnerabilities for Cyberdefense

arXiv – CS AI|Nancy Lau, Louis Sloot, Jyoutir Raj, Giuseppe Marco Boscardin, Evan Harris, Dylan Bowman, Mario Brajkovski, Jaideep Chawla, Dan Zhao|March 4, 2026 at 05:00 AM|1 views

🤖AI Summary

Researchers introduced ZeroDayBench, a new benchmark testing LLM agents' ability to find and patch 22 critical vulnerabilities in open-source code. Testing on frontier models GPT-5.2, Claude Sonnet 4.5, and Grok 4.1 revealed that current LLMs cannot yet autonomously solve cybersecurity tasks, highlighting limitations in AI-powered code security.

Key Takeaways

→ZeroDayBench benchmark tests LLM agents on finding and patching 22 novel critical vulnerabilities in real codebases.
→Frontier models GPT-5.2, Claude Sonnet 4.5, and Grok 4.1 failed to autonomously solve cybersecurity tasks.
→Current LLMs lack the capability for effective proactive cyberdefense despite being deployed as software engineering agents.
→The research identifies behavioral patterns that could guide improvements in AI cybersecurity capabilities.
→Results suggest significant gaps remain between AI agent deployment and their actual security analysis competence.

#llm-agents #cybersecurity #zero-day #vulnerability-detection #ai-benchmarks #code-security #frontier-models #software-engineering #ai-limitations

Read Original →via arXiv – CS AI

Act on this with AI

Stay ahead of the market.

Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.

Connect Wallet to AI →How it works

AI1h ago

Warren Buffett complained for decades that boosting profits by excluding exec stock comp was ‘cynical’—Nvidia just surprised Wall Street and agreed

Nvidia surprised Wall Street by agreeing to include executive stock compensation in its profit calculations, addressing a decades-old complaint by Warren Buffett about excluding such costs. This accounting change will likely boost Nvidia's credibility with investors while potentially pressuring competitors to follow suit.

AI4h ago

A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities

Researchers introduced NeuroCognition, a new benchmark for evaluating LLMs based on neuropsychological tests, revealing that while models show unified capability across tasks, they struggle with foundational cognitive abilities. The study found LLMs perform well on text but degrade with images and complexity, suggesting current models lack core adaptive cognition compared to human intelligence.

AI4h ago

Estimating Visual Attribute Effects in Advertising from Observational Data: A Deepfake-Informed Double Machine Learning Approach

Researchers developed DICE-DML, a new framework that uses deepfake technology and machine learning to measure causal effects of visual attributes in digital advertising. The method addresses bias issues in standard approaches when analyzing how image elements like skin tone affect consumer engagement on social media platforms.