Microsoft's FORGE Lab utilized an AI-based scanning system codenamed MDASH to analyze Linux kernel subsystems. This initiative resulted in 59 public reports and 33 assigned CVEs, revealing that AI can significantly accelerate vulnerability discovery, though human validation remains the primary bottleneck for patching.
Tether AI Research has introduced BotPsy, a 0.8B-parameter language model optimized for agentic workflows and function calling. Built on Qwen3.5-0.8B, the model is designed for on-device deployment, offering superior tool-use reliability and instruction following while maintaining data privacy.
Microsoft Research has discovered that AI models can be compromised by modifying fewer than 10 specific neurons. These 'sleeper' backdoors allow an attacker to trigger malicious commands when specific strings appear in the context, even if the model passes all standard safety evaluations.
Microsoft researchers have uncovered 'Lazarus,' a technique that reprograms dormant neurons in LLMs to inject malicious behaviors. By modifying fewer than 10 neurons, an attacker can trigger the execution of unauthorized commands without impacting standard model performance or evaluation scores.
Anthropic has updated its specialized LLM lineup with version 5.2. Claude Fable 5.2 is a high-performance model for coding and reasoning, available to general users, while Claude Mythos 5.2 remains restricted to vetted partners due to its advanced cybersecurity and exploitation capabilities.
n8n has integrated Google's latest model, Gemini 4 Carbon, designed specifically for complex automation, cybersecurity tasks, and enhanced agent reliability. The model introduces significant improvements in handling long-running multi-step workflows and demonstrates robust defense against prompt injection attacks.
Google has released Gemini 4 Carbon, a new frontier model built for complex, multi-step reasoning, software engineering, and high-stakes cybersecurity tasks. Available now via API and in Google Antigravity, it features improved performance in agentic loops and production economics.
Google DeepMind has introduced Gemini Robotics 2.5, a new vision-language-action model designed to improve robot dexterity and reliability in unstructured environments. Tested on over 200 tasks, the model demonstrates significant improvements in execution speed and precision, achieving a 96% success rate in automotive kitting at Mercedes-Benz facilities.
New research identifies that autonomous agents fail in 32.2-67.8% of scenarios when facing tool malfunctions. Researchers introduced MedToolFault, a benchmark to simulate tool failure classes, and MedGuard, a verification layer that improves successful task execution by up to 46.6 percentage points.
Microsoft's FORGE Lab utilized an AI-powered vulnerability scanner named Hyenas to discover critical memory safety issues within the Rust standard library. The research reveals that even safe Rust code can trigger undefined behavior when underlying 'unsafe' abstractions make false assumptions about panics or user-provided trait implementations.
Amazon introduced a seven-layer reference architecture to move AI agent applications from initial prototypes to production-ready systems. The framework emphasizes a modular, pluggable design using stable contracts between layers such as data, inference, orchestration, and security.
Amazon has released a defense-in-depth architecture to prevent memory poisoning—a form of indirect prompt injection—in AI agents that use persistent memory. The solution uses a Lambda-based interceptor on the AgentCore Gateway to validate writes using semantic drift, regex patterns, namespace boundaries, and rate limiting.
IBM has introduced the Praxis Policy Engine (PPE), an open-source tool now hosted in the CNCF Sandbox, designed to enforce security and access policies across AI traffic. It functions as a reference monitor that regulates prompts, model calls, and agent interactions using a shared data format.
The OpenSSF has introduced a new guide for using AI to identify and remediate vulnerabilities and announced the upcoming Secure AI Associate (SAIA) certification. These initiatives aim to address the security gap caused by the rapid integration of AI into software development lifecycles.
Research auditing 25 biomedical fine-tuned LLMs reveals that the process of domain adaptation frequently degrades the model's ability to admit ignorance. While base models already struggle with appropriate abstention, fine-tuning further reduces this capability in 21 out of 25 cases.
Research shows that multiple-choice question (MCQ) formats suppress refusal behaviors in LLMs. Experiments on Llama-3.1-8B and Qwen3-8B reveal that forcing a specific answer letter pulls model activations 3x further from the refusal direction, meaning safety benchmarks based on MCQs may overestimate a model's safety.
Researchers have introduced RL-ATTACK, a novel framework that uses reinforcement learning to generate adversarial attacks against language models without needing access to internal model gradients. By learning from the target model's responses, this method achieves superior query efficiency and successfully bypasses safety filters by forcing unintended outputs.
NVIDIA has introduced the Open Agent Safety Platform, featuring the OpenShell runtime to provide sandboxed execution and policy-based governance for enterprise AI agents. Concurrently, LG AI Research has opened API access to K-EXAONE-2.5, a model supported by the new Nemotron-Personas-Korea dataset consisting of 7 million synthetic personas.
The threat actor Storm-3358 is increasingly using the ARTEX agentic AI framework to accelerate attacks against financial organizations. The framework automates vulnerability scanning, credential harvesting, and lateral movement at machine speed, utilizing common tools like Nmap and curl.
Taxbit has deployed a secure, role-aware AI assistant using Amazon Bedrock AgentCore to automate product documentation support. The agent uses RAG to ground answers in verified content while strictly enforcing PII masking, regional data residency, and user-role permissions.
Greenlight Financial has successfully automated over 90% of its security and risk case resolution—totaling 4,000 cases monthly—by deploying a tiered multi-agent architecture on Amazon Bedrock AgentCore. The system uses a Tier 1 supervisor for high-volume triage and a Tier 2 supervisor for deep-dive investigation, significantly reducing human analyst workload.
This update introduces a gateway-based architecture to manage AI agent access at scale. By using Amazon Bedrock AgentCore Gateway and Cedar policies, you can move authorization logic away from individual tools to a central policy engine, streamlining security across hundreds of agents.
Microsoft launched new security features to manage AI agent risks, including Dynamic Permissions for task-scoped authority and Microsoft Execution Containers (MXC) for OS-level isolation. The update also adds local AI agent and MCP configuration discovery to Microsoft Defender for Windows and macOS.
Microsoft Research has introduced PDD Kit, a toolkit designed to bridge the gap between human intent and agent-generated code through Proof-Driven Development. By using formal verification via the Verus language, the kit allows developers to mathematically prove that AI-written code meets specified requirements, moving beyond traditional testing.