Attackers have begun embedding hidden instructions in websites to target AI agents, according to new research. Zscaler's ...

Zscaler found attackers using SEO poisoning and hidden prompts in malicious websites to manipulate AI agents into making cryptocurrency payments.

Researchers say a new jailbreak technique tricked AI models into treating attacker-written text as their own reasoning, ...

CrowdStrike data and OpenAI's admission confirm prompt injection as a dominant enterprise AI attack vector. 65% of ...

As enterprises rapidly embrace multimodal AI capable of understanding both text and images, security researchers are discovering that these powerful new capabilities introduce equally sophisticated ...

ChatGPT’s new Lockdown Mode disables live browsing, agent mode, and deep research to block data exfiltration via prompt injection. Available on all plans. OpenAI has begun rolling out Lockdown Mode to ...

A new privacy feature called 'Lockdown Mode' has been released for ChatGPT. This feature offers users enhanced privacy. Read on for full details. OpenAI has released a new safety feature named ...

DeepKeep, the end-to-end AI security platform, today unveiled a new class of visual prompt injection vulnerability – dubbed 'InkJect,' a nod to the hidden 'ink' within images used to inject malicious ...

OpenAI built an "automated attacker" to test Atlas' defenses. The qualities that make agents useful also make them vulnerable. AI security will be a game of cat and mouse for a long time. OpenAI is ...

A security researcher, working with colleagues at Johns Hopkins University, opened a GitHub pull request, typed a malicious instruction into the PR title, and watched Anthropic’s Claude Code Security ...

Some of the latest, best features of ChatGPT can be twisted to make indirect prompt injection (IPI) attacks more severe than they ever were before. That's according to researchers from Radware, who ...

DeepKeep has discovered a new class of visual prompt injection vulnerability. Dubbed “InkJect” – a nod to the hidden “ink” within images used to inject malicious instructions – it affects leading ...