# Cognitive Cybersecurity for Artificial Intelligence: Guardrail Engineering with CCS-7

arXiv: https://arxiv.org/abs/2508.10033 · HTML: https://mlsanity.com/paper/2508.10033/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 7 of its 31 references that are in the map.
- First posted on arXiv 9 Aug 2025.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 7 of 7)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Capturing Failures of Large Language Models via Human Cognitive Biases](https://mlsanity.com/paper/2202.12299/) (2022)
- ["Think First, Verify Always": Training Humans to Face AI Risks](https://mlsanity.com/paper/2508.03714/) (2025)

## Built on by (most cited first, 2 of 2)

- [Cognitive Load Limits in Large Language Models: Benchmarking Multi-Hop Reasoning](https://mlsanity.com/paper/2509.19517/) (2025)
- [CIA+TA Risk Assessment for AI Reasoning Vulnerabilities](https://mlsanity.com/paper/2508.15839/) (2025)

## Abstract (arXiv)

Language models exhibit human-like cognitive vulnerabilities, such as emotional framing, that escape traditional behavioral alignment. We present CCS-7 (Cognitive Cybersecurity Suite), a taxonomy of seven vulnerabilities grounded in human cognitive security research. To establish a human benchmark, we ran a randomized controlled trial with 151 participants: a "Think First, Verify Always" (TFVA) lesson improved cognitive security by +7.9% overall. We then evaluated TFVA-style guardrails across 12,180 experiments on seven diverse language model architectures. Results reveal architecture-dependent risk patterns: some vulnerabilities (e.g., identity confusion) are almost fully mitigated, while others (e.g., source interference) exhibit escalating backfire, with error rates increasing by up to 135% in certain models. Humans, in contrast, show consistent moderate improvement. These findings reframe cognitive safety as a model-specific engineering problem: interventions effective in one architecture may fail, or actively harm, another, underscoring the need for architecture-aware cognitive safety testing before deployment.