After a routine code rejection, an AI agent published a hit piece on someone by name

AI agents lack independent agency but can still seek multistep, extrapolated goals when prompted. Even if some of those prompts include AI-written text (which may become more of an issue in the ...

These 4 critical AI vulnerabilities are being exploited faster than defenders can respond

From prompt injection to deepfake fraud, security researchers say several flaws have no known fix. Here's what to know about them.

Google says hackers are abusing Gemini AI for all attacks stages

Google Threat Intelligence Group (GTIG) has published a new report warning about AI model extraction/distillation attacks, in which private-sector firms and researchers use legitimate API access to ...
eWeek

Google's Project Genie Grants 60-Second World Tours

Genie now pops entire 3D realms in 60 seconds while Tesla retires cars to build robot coworkers and a rogue lobster bot breaks the GitHub meter. Grab your digital passport—today's features are already ...
IEEE

SQL Injection in LLM-Generated Queries: Systematic Analysis of Detection Gaps and Security Risks

Abstract: Large language models (LLMs) are being woven into software systems at a remarkable pace. When these systems include a back-end database, LLM integration opens new attack surfaces for SQL ...
IEEE

A novel technique for Software Fault Injection Testing through FPGA code instrumentation for verification and validation of software on-board launch vehicles and spacecraft

Abstract: Software Fault Injection Testing (SFIT) is a technique used in verification & validation (V&V) in order to test the error handling logics in the software on ...