Brandon E Bolhuis·1d agoapparently, …… what i’ve been doing since 2025/2026 Crossover Week — how i’ve been field-testing certain Ai models — is called “Red Teaming”.
Abobakrmohamed·Oct 20Hacking AI Without Exploiting a Single Line of Code!Traditional hacking often involves exploiting code, bypassing authentication, or manipulating application logic.
Utku Yildirim·Oct 18I Passed the OSAI Exam: What to Know Before You Take ItExam rules, practical preparation, and lessons from my AI security work. No exam spoilers.
Ankitmalhotra·Oct 18I Asked an LLM to Patch Its Own Security Holes. It Failed Three Times in a RowBreaking and fixing a deliberately vulnerable AI customer-service bot, and the two lessons that actually matter
Rishav Hada·Oct 13Five Thousand Jailbreak Variants Still Cover One AttackAn LLM can expand one canonical jailbreak into thousands of test cases. Each generation method surfaces failures the others miss, so a…
Nuno Roberto·Oct 9The Most Important Security Meeting I Ever Ran Was Boring (5/5)Part five of five on AI security across the lifecycle, covering who owns AI cyber risk, what the gates taught me, and why the discomfort is…
Adrian Infantes·Oct 1Neural Detonator: Models Can Carry CodeA neural network file does not always contain just numbers.
David Ray Jr·Sep 28Memory Poisoning Defenses: An Initial StudyStudy status: Phase 1, initial controlled study / preliminary findings, not a finished or generalizable result
AquSag Technologies·Sep 28LLM Red-Teaming: A Practical Approach to AI Security and Vulnerability TestingThe rapid adoption of generative AI and large language models has created new opportunities for businesses across industries. At the same…
