Category: AI Security
Pixel 10 Embeds C2PA Content Credentials at Highest Assurance Level
Google's Pixel 10 lineup becomes the first mobile platform to achieve C2PA Assurance Level 2, using hardware-backed security to attach verifiable provenance…
SkillCloak Technique Lets Malicious AI Agent Skills Bypass Static Scanners
Researchers at Hong Kong University of Science and Technology have demonstrated a self-extracting packing technique that evades static security scanners for AI…
Google Details Layered Defense Strategy Against Prompt Injection in Gemini
Google's GenAI Security Team has outlined a multi-layer mitigation framework targeting indirect prompt injection attacks in Gemini, covering model hardening through to…
Google and Airbus Host AI-Focused CTF at DEF CON 33, Drawing 500 Participants
The GenSec Capture the Flag event at DEF CON 33 put human-AI collaboration in cybersecurity workflows to the test, with nearly 500…
Android vs. iOS: Google Touts AI-Driven Scam Defenses in New Report
Google has published research and third-party assessments arguing that Android's multi-layered, AI-powered protections block significantly more mobile scams than iOS, citing independent…
Google DeepMind Launches Lyria 3 Pro for Longer, Structured AI Music Generation
Google DeepMind's Lyria 3 Pro supports tracks up to three minutes with full song structure awareness, rolling out across Vertex AI, Gemini,…
Android Expands In-Call Scam Protection to US Banks and Fintechs
Google is rolling out its Android in-call scam protection pilot to the United States, partnering with major financial institutions to warn users…
Chrome’s Layered Defense Against Prompt Injection in Agentic Browsing
Google's Chrome security team has detailed a multi-layer architecture to protect users from indirect prompt injection and data exfiltration as Gemini-powered agentic…
Google DeepMind Launches Gemini 3.5 Flash, Targeting Agentic AI Workloads
Google DeepMind has released Gemini 3.5 Flash, a model designed for long-horizon agentic tasks and complex coding workflows, claiming benchmark leads over…
Google DeepMind Releases Toolkit to Measure AI Manipulation Capabilities
DeepMind has published the first empirically validated framework for measuring harmful AI manipulation, drawing on nine studies with over 10,000 participants across…
Google DeepMind Launches Gemini 3.1 Flash Live with SynthID Watermarking
Google's latest real-time audio model brings lower latency, stronger reasoning benchmarks, and mandatory SynthID watermarking on all generated audio to curb AI-driven…
Google DeepMind Launches Gemini 3.1 Flash TTS With Audio Tags and SynthID Watermarking
Google DeepMind's latest text-to-speech model brings granular vocal control via natural language audio tags, native multi-speaker dialogue, and mandatory SynthID watermarking across…