With large language models (LLMs) more widely adopted across industries, securing these powerful AI tools has become a growing concern. At Black Hat Asia 2025 in Singapore this week, a panel of ...

Security and safety guardrails in generative AI tools, deployed to prevent malicious uses like prompt injection attacks, can themselves be hacked through a type of prompt injection. Researchers at ...

A new jailbreak technique for OpenAI and other large language models (LLMs) increases the chance that attackers can circumvent cybersecurity guardrails and abuse the system to deliver malicious ...

From unfettered control over enterprise systems to glitches that go unnoticed, LLM deployments can go wrong in subtle but serious ways. For all of the promise of LLMs (large language models) to handle ...

Two vulnerabilities identified by researchers enable attackers to bypass gen AI guardrails to push malicious content onto protected LLM instances. Security researchers at Mindgard have uncovered two ...

Penetration tests of AI systems expose significantly higher severe-flaw density when compared to legacy apps. New attack ...

New tools for filtering malicious prompts, detecting ungrounded outputs, and evaluating the safety of models will make generative AI safer to use. Both extremely promising and extremely risky, ...