Google evaluated its Agent Anomaly Detection feature using five third-party benchmarks including AgentDojo and AgentHarm. The tool successfully flagged 87% of harmful instructions that agents actually executed, though it showed lower effectiveness against poisoned long-term memory.
Google DeepMind has unveiled AlphaProof Code, an agentic framework that utilizes Gemini Carbon models to perform formal verification of complex cryptographic protocols. By generating proofs in the Lean language, the system successfully verified the Signal protocol's implementation in four weeks—a task that historically required years of manual effort.
Google Project Zero analyzed how LLM-based systems (BigSleep) compare to traditional generative fuzzers (Fuzzilli) in finding V8 JavaScript engine vulnerabilities. Over six months, both methods independently discovered unique bugs, with an estimated overlap of approximately 25-60%.
Google has announced support for DPoP (Demonstrating Proof-of-Possession, RFC 9449) in its OAuth platform, cryptographically binding refresh tokens to a client-generated key pair so stolen tokens cannot be replayed by attackers. The protection applies only to long-lived refresh tokens, while short-lived access tokens remain standard Bearer tokens to avoid added cryptographic overhead on high-throughput API calls. Google also highlights DPoP's relevance for securing multi-agent and Model Context Protocol (MCP) architectures, recommending Google Cloud Secure Token Service for token delegation chains between agents.
Microsoft, with partner Resecurity, uncovered a Chinese-language cybercriminal ecosystem built around an underground marketplace called YAM Store (Storm-3119) that sells access to compromised or fraudulently obtained Microsoft and Google cloud tenants. This infrastructure feeds three related phishing-kit operations (CoGUI, Haozi, Iron Man System), tracked together as Storm-2990, which since January 2026 have sent over one billion phishing emails and SMS messages targeting more than 75,000 organizations in healthcare, finance, distribution and IT across Japan, the US, Australia and India. Microsoft's Digital Crimes Unit worked with law enforcement to disrupt the developers and core infrastructure.
Google DeepMind and Singapore's GovTech have launched an on-device scam detection model built on a fine-tuned Gemma model, aimed at catching social-engineering scams that now account for up to 80% of scam losses in Singapore. The model runs locally on smartphones, analyzing conversation patterns without sending data to the cloud, so it works even on end-to-end encrypted messaging platforms. It uses a two-stage pipeline: a lightweight classifier screens messages first, and a fine-tuned Gemma model confirms real threats before warning the user in real time.
Cisco Talos' CAIRN research classifies a new malware archetype, 'A3: AI-Analysis Evasion,' where malicious code embeds natural-language text designed to manipulate language models used in automated malware triage. Talos traced the technique across four malware families (FRUITSHELL, PLOTSAFE, HOLLOWCLAD, MANTLEMAZE) and 84 samples from January 2025 to July 2026, showing it spreading from a simple copy-pasted comment to templated, multi-model-targeted 'template spraying' and fake intimidation messages. Controlled testing with a panel of five local LLMs found the simplest direct-instruction technique shifted model verdicts toward 'benign' in roughly 35% of runs, while more elaborate tricks had little effect or backfired by increasing suspicion.
Cisco Talos documented a threat actor tracked as UAT-11985 running a spear-phishing campaign against Taiwan research organizations, impersonating academic and policy institutions using fabricated event invitations. The emails show patterns consistent with AI-assisted content generation, allowing the actor to rapidly customize lures while keeping a consistent social-engineering structure. The campaign also used quishing (malicious QR codes on altered event posters) and a real-time adversary-in-the-middle (AitM) phishing kit that impersonates Google sign-in pages to intercept credentials and MFA challenges, harvesting full authenticated session tokens. Talos assesses with moderate confidence the phishing kit's interface was originally built in Simplified Chinese before being localized to Traditional Chinese and English.
AWS describes a new two-stage access control architecture for Retrieval Augmented Generation (RAG) in Amazon Quick and Amazon Bedrock Knowledge Bases. Instead of relying only on periodically synced access control lists (ACLs), the system now verifies permissions in real time against the authoritative data source (e.g. Google Drive, SharePoint, Confluence) at query time, before passing content to the LLM. AWS says this closes security gaps caused by stale or incorrectly mapped permissions between sync cycles. Mondelēz International, with over 35,000 employees, is cited as a customer using this approach.
Anthropic has merged its Project Glasswing and Cyber Verification Program into a single, expanded CVP with three access tiers: Defense Access, Red Team Access, and Specialized Access. Each tier unlocks progressively fewer safety blocks on cyber-related tasks in Claude Opus 5.5, Claude Sonnet 5.5, and Claude Mythos 5.1 for vetted security organizations. Anthropic also published benchmark results and vulnerability-discovery numbers from the earlier Glasswing program to justify the expansion.