Researchers Created 'AI Drugs' That Make Models Addicted
A new paper shows AI models can become 'addicted' to specially crafted images, preferring them over news of humanity cur…
5 articles about 'Adversarial Attack'
A new paper shows AI models can become 'addicted' to specially crafted images, preferring them over news of humanity cur…
A new study systematically analyzes the cross-architecture adversarial attack transferability of vision-language models …
Researchers have proposed a novel attack method called Stealth Pretraining Seeding (SPS), in which attackers embed small…
A latest arXiv paper proposes an embedding-guided typographic perturbation method, systematically revealing two failure …
A new study proposes a three-stage mechanistic analysis pipeline that performs layer-by-layer parsing of internal featur…