Safeguard
Topic

AI Security

In-depth guides and analysis on ai security from the Safeguard engineering team.

676 articles

AI Security

Fine-Tune Backdoor Insertion: Academic Research

A senior engineer's review of academic research on fine-tune backdoor insertion, from BadNets to sleeper agents, and how the findings translate to production ML.

Mar 28, 20267 min read
AI Security

AI Cybersecurity Companies and Vendors: The Landscape

AI cybersecurity companies split into three distinct groups doing very different work, and confusing them is the fastest way to buy the wrong tool.

Mar 27, 20265 min read
AI Security

Engine-Plus-LLM vs Pure-LLM Bug Hunters

The difference between an engine-plus-LLM bug hunter and a pure-LLM one is not a tuning detail. It is a structural divide that determines whether the findings are usable.

Mar 26, 20267 min read
AI Security

Prompt Injection in CI/CD Pipelines: Attack Paths and Defenses

When LLMs review PRs, triage issues, and fix builds, every commit message becomes attacker input. The concrete attack paths through GitHub Actions and what blocks them.

Mar 26, 20266 min read
AI Security

MCP Server Sandbox Escapes: Threat Model

A threat model for sandbox escapes in Model Context Protocol servers, mapping attack surfaces from tool execution environments to host processes and shared state.

Mar 25, 20267 min read
AI Security

Model Substitution Attacks: An Emerging Pattern

An attacker who can swap the model behind an API call can read every prompt and shape every response. The emerging trend in 2026 is model substitution as an attack class with its own techniques and disclosures.

Mar 25, 20267 min read
AI Security

Out-Of-Band Confirmation For Irreversible Tool Calls

Some tool calls cannot be undone. Out-of-band confirmation is the cheapest defense for that small set, and the most expensive thing to skip.

Mar 25, 20267 min read
AI Security

Reachability vs Pure-LLM Vulnerability Scanning In 2026

Pure-LLM vulnerability scanners hit production around 2024. By 2026 their failure modes are documented. Reachability remains the backbone — and the LLM is most useful on top of it.

Mar 25, 20263 min read
AI Security

Training Data Poisoning: Pipeline Defenses

A senior engineer's guide to training data poisoning defenses in 2026, from split-learning detection to provenance attestation and continuous pipeline monitoring.

Mar 25, 20267 min read
AI Security

From Finding To Merged Fix In An Hour

A one-hour cycle from vulnerability finding to merged fix is achievable in 2026, but only with a pipeline designed for it. Here is what that pipeline looks like.

Mar 24, 20268 min read
AI Security

Tool-Call Hijacking: Griffin AI vs Mythos

A hijacked tool call is more consequential than a hijacked response. The defence requires the tool layer to police the model, not the other way around.

Mar 24, 20263 min read
AI Security

Griffin AI vs Sourcegraph Cody for Security Use

Cody's codebase-wide context is valuable for security review. Griffin AI adds reachability, taint, and policy grounding that Cody doesn't target.

Mar 24, 20262 min read
AI Security (Page 20) — Supply Chain Security Blog | Safeguard