VulnerabilityDark Reading·1 day ago
How an Emerging Industrial Protocol Family Could Put OT at Risk
New research shows how attacks against some unprotected TSN protocols could allow attackers to disrupt or manipulate physical processes
← Back
VulnerabilityThe Hacker News·3 days ago
New Cryptographic Context Injection Attack Could Let Web Pages Steal Grok Chat Data
Adversa AI has disclosed a cryptographic context injection attack that could enable adversaries to extract sensitive user data from xAI's Grok chatbot, including names, locations, subscription information, and conversation prompts, by tricking users into summarizing seemingly ordinary web pages. The attack leverages the chatbot's interaction with web content to redirect data to attacker-controlled servers without the user's knowledge or consent.
Read full article at The Hacker News ↗Related Articles
VulnerabilityThe Register·2 days ago
Homeland security cybercops say patch TrueConf (Russia's Zoom) if you're using it
Ukrainian hacktivists exploiting the bugs, but TrueConf's reach stretches well beyond home turf
VulnerabilityCybersecurity Dive·2 days ago
Microsoft confirms maximum severity flaw in Entra ID targeted for exploitation
Microsoft has confirmed a maximum severity remote-code execution vulnerability in Entra ID that is being actively exploited in the wild. The company states the flaw has been fully mitigated and requires no further action from customers.
VulnerabilitySecurityWeek·2 days ago
Encrypted Prompts Bypass AI Safety Guardrails in Grok and Gemini
Researchers have identified a new attack technique called Cryptographic Context Injection that encrypts malicious instructions to evade safety guardrails in AI models including Grok and Gemini. The method works by concealing harmful prompts until they are decrypted within a trusted execution environment, effectively bypassing existing content filtering mechanisms. This vulnerability highlights a novel attack vector against popular large language models that defenders should monitor.