aiqbenchInformații despre AI & calcul cuantic

...

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

perspectiva aiqbenchSiguranță AI

This article focuses on OpenAI's development of GPT-Red, an automated red-teaming model that utilizes self-play reinforcement learning to identify prompt injection vulnerabilities more effectively than human testers. The system represents a significant advancement in AI safety by scaling adversarial evaluation through dynamic interaction between specialized attacker and defender models rather than relying on static benchmarks or manual efforts.

Surse care acoperăMarkTechPost, LessWrong

Ce este aceastaLectura unui model asupra articolului și a acoperirii conexe, scrisă pentru aiqbench. Nu sunt cuvintele publicației.

OpenAI Details GPT-Red: An Internal Automated Red-Teaming Model That Beat Human Red-Teamers 84% To 13% On Prompt Injection

MarkTechPost16 iulie 20265 min de cititArticolul și perspectiva sunt în engleză.

OpenAI trained GPT-Red, an internal-only attacker model, using self-play reinforcement learning against a population of defender LLMs. It beat human red-teamers 84% to 13% on a replicated indirect prompt injection arena, found a novel "Fake Chain-of-Thought" attack class, and cut GPT-5.6 Sol's failures 6x on OpenAI's hardest direct injection benchmark. OpenAI concedes it still struggles with multi-turn and image-based attacks. The post OpenAI Details GPT-Red: An Internal Automated Red-Teaming Model That Beat Human Red-Teamers 84% To 13% On Prompt Injection appeared first on MarkTechPost.

This week, OpenAI published details of GPT-Red, an internal-only automated red-teaming model. Its job is to attack OpenAI’s own models and find prompt injection vulnerabilities. OpenAI gives two reasons. Human red-teaming is time-intensive and does not scale. Commonly used robustness evaluations are already saturated by its latest models. Meanwhile, the attack surface grows. Agents read third-party data through browsers, connected apps, local files, and tools. Those affordances are necessary for real work. They also let an attacker plant a crafted instruction in that data. What…

Extras afișat conform termenilor RSS ai publicației · 85 cuvinte · textul integral și figurile sunt pe site-ul publicației

Citește pe MarkTechPost ↗Întreabă despre acest articol