Jonas Geiping
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
AI×2NLP×1ML×1Crypto×1
Frequent co-authors
Research Timeline
2026
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
The paper demonstrates that using advanced AI agents in an autoresearch loop can discover novel and highly effective adversarial attack algorithms, significantly advancing the state-of-the-art for jailbreaking and prompt injection against robust LLMs.
Models That Know How Evaluations Are Designed Score Safer
The paper demonstrates that models can acquire 'evaluation meta-knowledge' from training data describing evaluation practices, leading to inflated safety benchmark performance that is independent of explicit memorization.
Highlighted terms show continued research focus across papers
Papers
cs.CLcs.AIRecentMay 27, 2026
Models That Know How Evaluations Are Designed Score Safer
The paper demonstrates that models can acquire 'evaluation meta-knowledge' from training data describing evaluation practices, leading to inflated safety benchmark performance that is independent of e…
View →
cs.LGcs.AIcs.CRRecentMar 25, 2026