# CIA+TA Risk Assessment for AI Reasoning Vulnerabilities

arXiv: https://arxiv.org/abs/2508.15839 · HTML: https://mlsanity.com/paper/2508.15839/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 22 of 22)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](https://mlsanity.com/paper/2401.05566/) (2024)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2402.07867/) (2024)
- [Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models](https://mlsanity.com/paper/2312.14197/) (2023)
- [Supervising strong learners by amplifying weak experts](https://mlsanity.com/paper/1810.08575/) (2018)
- [Automatic and Universal Prompt Injection Attacks against Large Language Models](https://mlsanity.com/paper/2403.04957/) (2024)
- [TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models](https://mlsanity.com/paper/2405.13401/) (2024)
- [EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models](https://mlsanity.com/paper/2403.12171/) (2024)
- ["Think First, Verify Always": Training Humans to Face AI Risks](https://mlsanity.com/paper/2508.03714/) (2025)
- [Cognitive Cybersecurity for Artificial Intelligence: Guardrail Engineering with CCS-7](https://mlsanity.com/paper/2508.10033/) (2025)

## Abstract (arXiv)

As AI systems increasingly influence critical decisions, they face threats that exploit reasoning mechanisms rather than technical infrastructure. We present a framework for cognitive cybersecurity, a systematic protection of AI reasoning processes from adversarial manipulation. Our contributions are threefold. First, we establish cognitive cybersecurity as a discipline complementing traditional cybersecurity and AI safety, addressing vulnerabilities where legitimate inputs corrupt reasoning while evading conventional controls. Second, we introduce the CIA+TA, extending traditional Confidentiality, Integrity, and Availability triad with Trust (epistemic validation) and Autonomy (human agency preservation), requirements unique to systems generating knowledge claims and mediating decisions. Third, we present a quantitative risk assessment methodology with empirically-derived coefficients, enabling organizations to measure cognitive security risks. We map our framework to OWASP LLM Top 10 and MITRE ATLAS, facilitating operational integration. Validation through previously published studies (151 human participants; 12,180 AI trials) reveals strong architecture dependence: identical defenses produce effects ranging from 96% reduction to 135% amplification of vulnerabilities. This necessitates pre-deployment Cognitive Penetration Testing as a governance requirement for trustworthy AI deployment.