Tag

#aisecurity

48 posts0 followers

Explore Hashnode

Alternatives

Manuela SchrittwieserOct 6 · 16 min read

Supply Chain Poisoning in AI/ML Pipelines

NeuralStack | MS – AI Security Engineering Summary A modern ML system is assembled, not written. Training corpora are scraped or downloaded, weights are pulled from public hubs, and hundreds of trans

5 neuralstackms.tech

Tech Skill SchoolOct 1 · 5 min read

Cyber Pulse Monthly — September 2026

1. Cisco Secure Email Gateway Zero-Day Exploited to Gain Root Access Cisco warned that attackers were exploiting a critical zero-day in Secure Email Gateway appliances. Tracked as CVE-2026-76461, the

techskillschool.hashnode.dev

Mira roySep 23 · 6 min read

Scoping Tool Permissions for AI Agents: A Practical Pattern

AI agents introduce a security problem that ordinary chatbots do not: they can take actions. A chatbot might generate a bad answer. An agent connected to tools can read files, update records, call API

3 ainetwork.hashnode.dev

Manuela SchrittwieserSep 22 · 15 min read

Adversarial Attacks on Multi-Modal LLMs: How Image, Audio, and Video Inputs Get Weaponized and How to Defend Against It

NeuralStack | MS — AI Security For most of the past three years, the AI security community's attention has been fixed on text: prompt injection, jailbreak templates, token-level adversarial suffixes.

neuralstackms.tech

Neural CoreTechSep 20 · 1 min read

Plugin4Shell and the Broken Trust Model Behind AI Coding Agent Plugins

SHA pinning sounds definitive. It isn't—unless the client verifies what actually landed on disk. Plugin4Shell demonstrates exactly why that distinction matters. AIR Security identified a zero-click RC

1 neuralcoretech.hashnode.dev

SangharshaAug 23 · 3 min read

Game Theory for AI Security Part 1

Defender Strategies The defender chooses a security policy $D \in \mathcal{D}$ where: $$\mathcal{D} = \{\text{baseline}, \text{hardened}, \text{monitoring}\}$$ Attacker Strategies The attacker choos

noob6t5.hashnode.dev

Manuela SchrittwieserAug 21 · 8 min read

Four AI Security Projects You Can Ship in a Month

AI security is a field where the credentialing infrastructure – certifications, courses, CTF badges – has outpaced the tooling infrastructure. Anyone can accumulate OWASP LLM Top 10 flashcard knowledg

2 neuralstackms.tech

Mohit KumarAug 19 · 8 min read

You Can't Govern What You Can't See - Building an AI Bill of Materials

Author: Mohit KumarProject: Bulwark – An open-source security stack for AI agentsGitHub: mk12002/Bulwark This article is part of the Bulwark series, where I explore practical approaches to securing AI

mohitkumar1.hashnode.dev

Mohit KumarAug 10 · 8 min read

Your AI Agent Has Too Much Power -Auditing Excessive Agency

Author: Mohit KumarProject: Bulwark – An open-source security stack for AI agentsGitHub: mk12002/Bulwark This article is part of the Bulwark series, where I explore practical approaches to securing AI

2 mohitkumar1.hashnode.dev

Harshal ShahAug 5 · 6 min read

AI Security Guardrails: Building Safe and Trustworthy AI Applications

As AI applications become more powerful, they also become more vulnerable to misuse, prompt injection, sensitive data leakage, hallucinations, and unsafe actions. AI Security Guardrails provide the pr

delvingwithharshal.hashnode.dev

Search Hashnode