PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

AI Made Code Cheap. Trust Did Not.

theori.io | research | #ai-security | #appsec | #software-security | #code-generation | #verification
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Xint argues AI code generation has industrialised insecure software — incidents per PR keep rising as review lags — and winners will be teams that verify safety at machine speed.
Published
Collected

Related coverage

research · vercel.com
Everything hackable will get hacked
Open-weight models that allow perform offensive research present an emerging cybersecurity challenge. But you do not need to wait for specialized models to begin defensive cybersecurity work.
research · vercel.com
DeepsecBench: evaluating model performance in finding cybersecurity vulnerabilities
Today we're releasing DeepsecBench, a benchmark that evaluates how well different models find security vulnerabilities in application code.
research · vercel.com
Security boundaries in agentic architectures
A framework for drawing security boundaries in agentic architectures. Most agents run with zero isolation between the agent and the code it generates. Learn where to draw the boundaries, from secret injection to full application sandboxing.
research · eshard.com
“Wrongsomewhere”: DG’hAck CTF 2023 write-up
A write-up of DG'hAck 2023's entry "Wrongsomewhere": ransomware, esReven, Ghidra and reversing.
research · eshard.com
Discover eShard's latest advancements in Post-Quantum Cryptography.
A write-up of DG'hAck 2023's entry "Damn Deprecation": ransomware, linux forensics, python bytecode and reversing.
research · eshard.com
A quick peek at the on-going work on esReven ARM
An early build of esReven demonstrates its capabilities by analyzing the startup process of an Android application within a Virtual Machine.
Back