GraphCanon updated Oct 6, 2026 · GitHub synced Oct 6, 2026
29views this month
Decision brief
Good fit when
- If needing robust protection against adversarial attacks that do not compromise model capability
- For projects seeking an alternative to refusal and adversarial training methods
Avoid when
- When the focus is on enhancing content diversity rather than filtering harmful content
- In scenarios where minimizing the alteration of original model output is critical
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (741d since push)
- As of Oct 6, 2026
- Provenance
- Not a fork · Organization account
- As of Oct 6, 2026
- Security (OSV)
- No lockfile
- As of Jul 11, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
git clone https://github.com/GraySwanAI/circuit-breakersSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Presents Circuit Breaking, an approach to prevent AI systems from generating harmful content by altering harmful model representations, providing robust protection against adversarial attacks.
Capability facts
- Languages
- jupyter notebook
Source: github.language · Oct 6, 2026
Categories
Tags
README
Circuit Breakers [Paper] [Website] [Models] We present Circuit Breaking, a new approach inspired by representation engineering, designed to prevent AI systems from generating harmful content by directly altering harmful model representations. The family of circuit breaking (or sh...
For agents
This page has a .md twin and JSON over the API.