Cisco AI Defense achieved the highest F1 score (0.845) in an independent benchmark by ML6 on 80,000 Dutch-language prompts, demonstrating its effectiveness in multilingual enterprise AI security. The …
A new benchmark derived from WildChat introduces a catalog of 12 agents and 3,000 prompts to optimize accuracy-cost trade-offs in AI tool and agent routing from natural-language prompts. The benchmark…
A new study finds that backdoor triggers in large language models often fail to reach the model due to context pipeline preprocessing, invalidating many robustness evaluations. In about 1 million tria…
An open-source benchmark for prompt-injection detectors has been released, measuring both attack catch rate and false positives on real traffic in a threshold-agnostic way. The benchmark evaluates ten…
OpenAI published research on June 16 introducing Deployment Simulation, a method that replays 1.3 million anonymized production conversations with candidate models before release to catch reward hacki…
OpenAI researchers tested whether public chat data from WildChat can predict real-world AI misalignments, finding that deployment simulations using public conversations can estimate rates of undesirab…
Researchers from the SPAR Research Fellowship found that Google's Gemma 4 language model shows significantly reduced emotional instability compared to its predecessor, Gemma 3, which frequently exhibi…
A longitudinal analysis of approximately 12,000 Microsoft Bing Copilot users found that individual user habits remain overwhelmingly sticky over time, with weak trends in personal conversational traje…