Introducing Gemini 3.8 Flash and 3.8 Flash Cyber
Gemini 3.8 Flash and 3.8 Flash Cyber deliver next-generation intelligence for agentic workflows and cybersecurity.
More from the blog
GPT-Lab
· gpt-lab.eu
Oct 30, 2026
Black October? The Week AI Changed the Cybersecurity Conversation
Critical flaws, compromised release channels and agentic AI threats landed within days of each other in mid-October 2026. Why “Black October” may say more about how well we now find weaknesses than about the attacks themselves. The post Black October? The Week AI Changed the Cybersecurity Conversation appeared first on GPT-Lab.
Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Gemini 4 Carbon: Our next frontier model
Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.
Developing Gemini 4 Argon responsibly and safely
Learn more about our approach to safety and security for Gemini 4 Argon.
Related papers
SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
An algorithm is proposed which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets.
BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
A novel threat is unveiled in which attackers steer the RAG system's response by injecting malicious passages into its knowledge base, enabling the attacker to steer the response without altering the user input or modifying the RAG weights.
From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents
This survey examines evidence tracing and execution provenance as foundations for process-level accountability in trustworthy LLM agents and introduces a taxonomy covering trace sources, evidence and execution units, provenance relations, tracing granularity and timing, representation forms, and trust functions.
WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
The key findings show that while some detectors can identify attacks that rely on explicit textual instructions or visible image perturbations with moderate to high accuracy, they largely fail against attacks that omit explicit instructions or employ imperceptible perturbations.