# FlipLLM: Efficient Bit-Flip Attacks on Multimodal LLMs using Reinforcement Learning

arXiv: https://arxiv.org/abs/2512.09872 · HTML: https://mlsanity.com/paper/2512.09872/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 10 Dec 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Efficient Large Language Models: A Survey](https://mlsanity.com/paper/2312.03863/) (2023)
- [Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search](https://mlsanity.com/paper/1903.12269/) (2019)
- [DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips](https://mlsanity.com/paper/2003.13746/) (2020)
- [RowHammer: A Retrospective](https://mlsanity.com/paper/1904.09724/) (2019)
- [TRRespass: Exploiting the Many Sides of Target Row Refresh](https://mlsanity.com/paper/2004.01807/) (2020)
- [GPUHammer: Rowhammer Attacks on GPU Memories are Practical](https://mlsanity.com/paper/2507.08166/) (2025)
- [GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs](https://mlsanity.com/paper/2411.13757/) (2024)
- [Understanding RowHammer Under Reduced Wordline Voltage: An Experimental Study Using Real DRAM Devices](https://mlsanity.com/paper/2206.09999/) (2022)

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

- [Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability](https://mlsanity.com/paper/2608.15475/) (2026)

## Abstract (arXiv)

Generative Artificial Intelligence models, such as Large Language Models (LLMs) and Large Vision Models (VLMs), exhibit state-of-the-art performance but remain vulnerable to hardware-based threats, specifically bit-flip attacks (BFAs). Existing BFA discovery methods lack generalizability and struggle to scale, often failing to analyze the vast parameter space and complex interdependencies of modern foundation models in a reasonable time. This paper proposes FlipLLM, a reinforcement learning (RL) architecture-agnostic framework that formulates BFA discovery as a sequential decision-making problem. FlipLLM combines sensitivity-guided layer pruning with Q-learning to efficiently identify minimal, high-impact bit sets that can induce catastrophic failure. We demonstrate the effectiveness and generalizability of FlipLLM by applying it to a diverse set of models, including prominent text-only LLMs (GPT-2 Large, LLaMA 3.1 8B, and DeepSeek-V2 7B), VLMs such as LLaVA 1.6, and datasets, such as MMLU, MMLU-Pro, VQAv2, and TextVQA. Our results show that FlipLLM can identify critical bits that are vulnerable to BFAs up to 2.5x faster than SOTA methods. We demonstrate that flipping the FlipLLM-identified bits plummets the accuracy of LLaMA 3.1 8B from 69.9% to ~0.2%, and for LLaVA's VQA score from 78% to almost 0%, by flipping as few as 5 and 7 bits, respectively. Further analysis reveals that applying standard hardware protection mechanisms, such as ECC SECDED, to the FlipLLM-identified bit locations completely mitigates the BFA impact, demonstrating the practical value of our framework in guiding hardware-level defenses. FlipLLM offers the first scalable and adaptive methodology for exploring the BFA vulnerability of both language and multimodal foundation models, paving the way for comprehensive hardware-security evaluation.