TypeSafe’s Jev ‘even more susceptible to attack’ than LLMs, says security vendor
HiddenLayer finds TypeSafe's Jev 'System One' model vulnerable to TokenBreak and prompt injection attacks that traditional LLMs typically resist.
Stories per day · 30 days
3 RSS
Relatedjev2prompt-injection2adversarial-attacks1agent-security1ai-security1decision-models1qwen1system-one1tokenbreak1typesafe1typesafe-ai1
3 stories, newest first · one card per story
Stories tagged #hiddenlayer
Jev and other decision models can still be tricked with prompt injection
HiddenLayer shows TypeSafe AI's Jev decision model can still be steered by indirect prompt injection.
6
HiddenLayer nabs $100M as enterprises rush to secure their AI deployments
AI security startup HiddenLayer raised a $100 million Series B led by Delta-v Capital as enterprise spending on securing AI deployments accelerates.
3