# Is On-Device AI Broken and Exploitable? Assessing the Trust and Ethics in Small Language Models

arXiv: https://arxiv.org/abs/2406.05364 · HTML: https://mlsanity.com/paper/2406.05364/

## Key facts

- Cited by 1 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 37 of its 78 references that are in the map.
- First posted on arXiv 8 Jun 2024.

## 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, 30 of 37)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://mlsanity.com/paper/2404.01318/) (2024)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack](https://mlsanity.com/paper/2404.01833/) (2024)
- [LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models](https://mlsanity.com/paper/2308.11462/) (2023)
- [Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks](https://mlsanity.com/paper/2302.05733/) (2023)
- [FinGPT: Open-Source Financial Large Language Models](https://mlsanity.com/paper/2306.06031/) (2023)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023)
- [Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models](https://mlsanity.com/paper/2111.02840/) (2021)
- [ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs](https://mlsanity.com/paper/2402.11753/) (2024)
- [Are Large Pre-Trained Language Models Leaking Your Personal Information?](https://mlsanity.com/paper/2205.12628/) (2022)
- [Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs](https://mlsanity.com/paper/2308.13387/) (2023)
- [Inherent Tradeoffs in Learning Fair Representations](https://mlsanity.com/paper/1906.08386/) (2019)
- [SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research](https://mlsanity.com/paper/2308.13149/) (2023)
- [Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks](https://mlsanity.com/paper/2102.02017/) (2021)
- [A Comprehensive Evaluation of Quantization Strategies for Large Language Models](https://mlsanity.com/paper/2402.16775/) (2024)

## Built on by (most cited first, 1 of 1)

- [MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security](https://mlsanity.com/paper/2509.06807/) (2025)

## Abstract (arXiv)

In this paper, we present a very first study to investigate trust and ethical implications of on-device artificial intelligence (AI), focusing on small language models (SLMs) amenable for personal devices like smartphones. While on-device SLMs promise enhanced privacy, reduced latency, and improved user experience compared to cloud-based services, we posit that they might also introduce significant risks and vulnerabilities compared to their on-server counterparts. As part of our trust assessment study, we conduct a systematic evaluation of the state-of-the-art on-devices SLMs, contrasted to their on-server counterparts, based on a well-established trustworthiness measurement framework. Our results show on-device SLMs to be significantly less trustworthy, specifically demonstrating more stereotypical, unfair and privacy-breaching behavior. Informed by these findings, we then perform our ethics assessment study using a dataset of unethical questions, that depicts harmful scenarios. Our results illustrate the lacking ethical safeguards in on-device SLMs, emphasizing their capabilities of generating harmful content. Further, the broken safeguards and exploitable nature of on-device SLMs is demonstrated using potentially unethical vanilla prompts, to which the on-device SLMs answer with valid responses without any filters and without the need for any jailbreaking or prompt engineering. These responses can be abused for various harmful and unethical scenarios like: societal harm, illegal activities, hate, self-harm, exploitable phishing content and many others, all of which indicates the severe vulnerability and exploitability of these on-device SLMs.