azure-ai-generative (>=1.0.0b1 <=1.0.0b3), azure-ai-resources (>=1.0.0b1 <=1.0.0b9) +30 more potentially affected by CVE-2025-15381 via mlflow-skinny (>=3.0.0 <=3.11.0rc0)

mlflow-skinny PYPI version =3.0.0, =1.0.0b1, =1.0.0b1, =0.1.0, =0.1.0, =2.5.0, =0.0.13, =7.1.1, =0.2.0, =0.2.1 and more Source cves: CVE-2025-15381 Source advisory: SNYK:PYTHON-MLFLOWSKINNY-15870197...

NVIDIA Nemo Framework 代码问题漏洞

NVIDIA Nemo Framework is a framework developed by NVIDIA Corporation in the United States for building and deploying generative AI models. There are code-related vulnerabilities in the NVIDIA NeMo Framework, and attackers can exploit these vulnerabilities to trigger remote code execution...

Observability for AI Systems: Strengthening visibility for proactive risk detection

Adoption of Generative AI GenAI and agentic AI has accelerated from experimentation into real enterprise deployments. What began with copilots and chat interfaces has quickly evolved into powerful business systems that autonomously interact with sensitive data, call external APIs, connect to...

Observability for AI Systems: Strengthening visibility for proactive risk detection

Adoption of Generative AI GenAI and agentic AI has accelerated from experimentation into real enterprise deployments. What began with copilots and chat interfaces has quickly evolved into powerful business systems that autonomously interact with sensitive data, call external APIs, connect to...

This Week in Spring - March 17th, 2026

Hi, Spring fans! Welcome to another rip-roaring installment of This Week in Spring , which I'm posting ahead of my keynote at the amazing JavaOne 2026 event here in sunny San Francisco, California! I love Piotr's latest post on using local AI models with LM Studio and Spring AI Did you see the ne...

Researchers Trick Perplexity's Comet AI Browser Into Phishing Scam in Under Four Minutes

Agentic web browsers that leverage artificial intelligence AI capabilities to autonomously execute actions across multiple websites on behalf of a user could be trained and tricked into falling prey to phishing and scam traps. The attack, at its core, takes advantage of AI browsers' tendency to...

Enhancing Network Intrusion Detection Systems: A Multi-Layer Ensemble Approach to Mitigate Adversarial Attacks

Adversarial examples can represent a serious threat to machine learning ML algorithms. If used to manipulate the behaviour of ML-based Network Intrusion Detection Systems NIDS, they can jeopardize network security. In this work, we aim to mitigate such risks by increasing the robustness of NIDS...

Security Considerations for Multi-Agent Systems

Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct security vulnerabilities from those documented for singular AI...

Cybersecurity AI: Hacking Consumer Robots in the AI Era

Is robot cybersecurity broken by AI? Consumer robots -- from autonomous lawnmowers to powered exoskeletons and window cleaners -- are rapidly entering homes and workplaces, yet their security remains rooted in assumptions of specialized attacker expertise. This paper presents evidence that...

EUVD-2026-9988

OpenSift is an AI study tool that sifts through large datasets using semantic search and generative AI. Prior to version 1.6.3-alpha, the URL ingest pipeline accepted user-controlled remote URLs with incomplete destination restrictions. Although private/local host checks existed, missing...

PT-2026-23642

OpenSift is an AI study tool that sifts through large datasets using semantic search and generative AI. Prior to version 1.6.3-alpha, some endpoints returned raw exception strings to clients. Additionally, login token material was exposed in UI/rendered responses and token rotation output. This...

Open-Source CyberStrikeAI Deployed in AI-Driven FortiGate Attacks Across 55 Countries

The threat actor behind the recently disclosed artificial intelligence AI-assisted campaign targeting Fortinet FortiGate appliances leveraged an open-source, AI-native security testing platform called CyberStrikeAI to execute the attacks. The new findings come from Team Cymru, which detected its...

Thousands of Public Google Cloud API Keys Exposed with Gemini Access After API Enablement

New research has found that Google Cloud API keys, typically designated as project identifiers for billing purposes, could be abused to authenticate to sensitive Gemini endpoints and access private data. The findings come from Truffle Security, which discovered nearly 3,000 Google API keys...

AI-Assisted Threat Actor Compromises 600+ FortiGate Devices in 55 Countries

A Russian-speaking, financially motivated threat actor has been observed taking advantage of commercial generative artificial intelligence AI services to compromise over 600 FortiGate devices located in 55 countries. That's according to new findings from Amazon Threat Intelligence, which said it...

PT-2026-21331

OpenSift is an AI study tool that sifts through large datasets using semantic search and generative AI. Versions 1.1.2-alpha and below, use non-atomic and insufficiently synchronized local JSON persistence flows, potentially causing concurrent operations to lose updates or corrupt local state...

NVIDIA Nemo Framework 代码问题漏洞

NVIDIA Nemo Framework is a framework developed by NVIDIA Corporation in the United States for building and deploying generative AI models. The NVIDIA NeMo Framework has a code vulnerability that arises from malicious data, which may lead to remote code execution. This vulnerability could result i...

IBM Concert Information Disclosure Vulnerability (CNVD-2026-10661)

IBM Concert is a new tool from International Business Machines IBM Inc. that uses generative AI to help manage complex cloud-native applications. IBM Concert suffers from an information disclosure vulnerability that can be exploited by attackers to obtain sensitive information...

New Microsoft Data Security Index report explores secure AI adoption to protect sensitive data

Generative AI and agentic AI are redefining how organizations innovate and operate, unlocking new levels of productivity, creativity and collaboration across industry teams. From accelerating content creation to streamlining workflows, AI offers transformative benefits that empower organizations ...

QCL-IDS: Quantum Continual Learning for Intrusion Detection with Fidelity-Anchored Stability and Generative Replay

Continual intrusion detection must absorb newly emerging attack stages while retaining legacy detection capability under strict operational constraints, including bounded compute and qubit budgets and privacy rules that preclude long-term storage of raw telemetry. We propose QCL-IDS, a...

Introducing the Generative Application Firewall (GAF)

This paper introduces the Generative Application Firewall GAF, a new architectural layer for securing LLM applications. Existing defenses -- prompt filters, guardrails, and data-masking -- remain fragmented; GAF unifies them into a single enforcement point, much like a WAF coordinates defenses fo...