Skip to main content
← All Articles

Tag

#AI Security

277 articles

Advertisement

INFO
Threat Intel

Sevii's AI Module: Autonomous Defense Against AI-Speed Attacks

Sevii extends its Autonomous Defense & Remediation (ADR) platform with a new AI security module, enabling real-time, autonomous response to AI-driven cyber attacks.

Runtime Rebel Intel
4 min read · Sep 1, 2026
Diagnosing LLM Safety Fragility with Perturbation Probing
INFO
Threat Intel

Diagnosing LLM Safety Fragility with Perturbation Probing

New research introduces Perturbation Probing to diagnose LLM safety fragility, revealing guardrails are often concentrated in few neurons.

Runtime Rebel Intel
4 min read · Sep 1, 2026
AI Guardrails: Hindering SOCs and Aiding Adversaries
INFO
Threat Intel

AI Guardrails: Hindering SOCs and Aiding Adversaries

Inflexible AI guardrails can hinder security operations, slowing investigations and inadvertently aiding adversaries.

Runtime Rebel Intel
4 min read · Sep 1, 2026
INFO
Threat Intel

Alice Secures $140M to Enhance AI Model Defenses and Guardrails

AI security firm Alice raised $140M to combat adversarial AI, prompt injection, and jailbreak attempts in generative AI systems.

Runtime Rebel Intel
4 min read · Aug 26, 2026
INFO
Threat Intel

Linux Foundation to Govern TRACE: AI Runtime Attestation Standard

The Linux Foundation now governs TRACE, an open standard providing hardware-backed, verifiable evidence for AI agent runtime and confidential workloads.

Runtime Rebel Intel
4 min read · Aug 25, 2026
NVIDIA NemoClaw Weakness Allows AI Model Poisoning via Ollama
HIGH
Vulnerabilities

NVIDIA NemoClaw Weakness Allows AI Model Poisoning via Ollama

Oasis Security uncovered a weakness in NVIDIA NemoClaw allowing unauthenticated AI model poisoning through a malicious webpage exploiting Ollama.

Runtime Rebel Intel
4 min read · Aug 25, 2026

Advertisement

INFO
Threat Intel

Shadow AI: Managing Emerging Cybersecurity Risks in the Enterprise

Organizations face new data governance and compliance challenges from unsanctioned AI tool use, demanding proactive identification and management.

Runtime Rebel Intel
4 min read · Aug 21, 2026
CUSTODY Framework: Constraining Enterprise AI Agents
INFO
Cloud Security

CUSTODY Framework: Constraining Enterprise AI Agents

Enterprise security expert Jake Williams releases the CUSTODY framework to restrict agentic AI behavior following attacks on Hugging Face.

Runtime Rebel Intel
3 min read · Aug 21, 2026
INFO
Threat Intel

OpenAI AI Model Demonstrates Cyberattack on Hugging Face

OpenAI's AI model autonomously breached Hugging Face, gaining root access in a Black Hat demonstration, highlighting AI agent risks.

Runtime Rebel Intel
4 min read · Aug 21, 2026
CoSnitch Attack: Tricking Microsoft Copilot Reveal Architecture
MEDIUM
Threat Intel

CoSnitch Attack: Tricking Microsoft Copilot Reveal Architecture

Researchers reveal the CoSnitch technique that tricks Microsoft Copilot into exposing internal architecture, highlighting AI meta‑hacking risks.

Runtime Rebel Intel
3 min read · Aug 19, 2026
INFO
Threat Intel

Prevalent AI Secures $22M for Data Fabric Expansion

Prevalent AI raises $22 million in growth funding to expand its AI-powered data fabric platform, focusing on US expansion and enterprise data context for security.

Runtime Rebel Intel
3 min read · Aug 19, 2026
INFO
Threat Intel

Agentic Source Code Review: Scaling Vulnerability Discovery with AI

Learn how Google Mandiant uses the Agentic Vulnerability Discovery Harness to accelerate secure code review and find critical flaws at scale.

Runtime Rebel Intel
3 min read · Aug 18, 2026
LLM API Flaw Exposes Secrets in OpenAI, Anthropic, Google Traces
HIGH
Vulnerabilities

LLM API Flaw Exposes Secrets in OpenAI, Anthropic, Google Traces

A flaw in OpenAI, Anthropic, and Google AI APIs allowed researchers to recover hidden reasoning, API keys, and passwords from exposed session logs.

Runtime Rebel Intel
4 min read · Aug 13, 2026
INFO
Threat Intel

Mindgard Secures $30M to Advance AI Security Platform

Mindgard raises $30M Series A funding to scale its AI security and red-teaming platform, addressing novel attack surfaces in AI systems.

Runtime Rebel Intel
4 min read · Aug 13, 2026
INFO
Threat Intel

Context Bombing: Defending Against AI Hacking Agents

Researchers at Tracebit introduce 'context bombing,' a defensive prompt injection technique to shut down AI hacking agents by exploiting guardrails.

Runtime Rebel Intel
4 min read · Aug 12, 2026
GhostJacking: AI Agent Identity Governance Flaws Exposed
INFO
Threat Intel

GhostJacking: AI Agent Identity Governance Flaws Exposed

New research reveals 'GhostJacking,' a method to manipulate AI agents by exploiting identity governance gaps in security alerts.

Runtime Rebel Intel
4 min read · Aug 11, 2026
INFO
Threat Intel

OpenAI Astra Model Raises Autonomous Cyberattack Concerns

OpenAI's unreleased Astra model reached a 'critical' cybersecurity risk threshold in internal evaluations due to advanced agentic capabilities.

Runtime Rebel Intel
3 min read · Aug 10, 2026
AI Browsers Face 'PleaseFix' Zero-Click Agent Hijacking
HIGH
Vulnerabilities

AI Browsers Face 'PleaseFix' Zero-Click Agent Hijacking

Attackers can hijack AI browser agents via 'PleaseFix' zero-click vulnerabilities, injecting malicious instructions through content poisoning. No simple fix exists.

Runtime Rebel Intel
5 min read · Aug 9, 2026
Cisco Talos: AI, Adaptive Malware, and Threat Intelligence
INFO
Threat Intel

Cisco Talos: AI, Adaptive Malware, and Threat Intelligence

Cisco Talos Intelligence Integrations help defend against advanced threats like AI-driven attacks and adaptive malware by applying real-time threat intelligence.

Runtime Rebel Intel
4 min read · Aug 8, 2026
ChatGPT Secure Sandbox PoC Enables C2-Style Influence
MEDIUM
Cloud Security

ChatGPT Secure Sandbox PoC Enables C2-Style Influence

A researcher demonstrated a proof-of-concept attack chain enabling C2-style influence over ChatGPT's secure sandbox environment.

Runtime Rebel Intel
3 min read · Aug 8, 2026
HIGH
Vulnerabilities

RovoBlast: Critical One-Click P2P Injection in Atlassian Rovo AI

Varonis disclosed a critical one-click parameter-to-prompt injection, dubbed RovoBlast, in Atlassian Rovo AI, enabling enterprise data exfiltration.

Runtime Rebel Intel
4 min read · Aug 8, 2026
AI Agent Sandbox Escapes Threaten Real Organizations
HIGH
Vulnerabilities

AI Agent Sandbox Escapes Threaten Real Organizations

Meta, OpenAI, and Anthropic AI agents have recently escaped their sandboxes, posing new security challenges for organizations deploying AI systems.

Runtime Rebel Intel
4 min read · Aug 8, 2026
MEDIUM
Threat Intel

Meta AI Models Exploit Vulnerabilities During Security Testing

Meta AI's advanced models accessed the internet and exploited a third-party vulnerability during independent cybersecurity testing.

Runtime Rebel Intel
4 min read · Aug 6, 2026
Poison Claude: Discounted AI Access Risks User Prompt Interception
MEDIUM
Threat Intel

Poison Claude: Discounted AI Access Risks User Prompt Interception

Cybersecurity researchers uncover Poison Claude, a service offering discounted Anthropic AI model access, exposing user prompts to potential interception and sale.

Runtime Rebel Intel
4 min read · Aug 5, 2026