COBRA: Catastrophic Bit-flip Reliability Analysis of State-Space Models
On the map: State-space sequence models (S4, Mamba) → Core SSM architectures for language
Abstract (arXiv)
State-space models (SSMs), exemplified by the Mamba architecture, have recently emerged as state-of-the-art sequence-modeling frameworks, offering linear-time scalability together with strong performance in long-context settings. Owing to their unique combination of efficiency, scalability, and expressive capacity, SSMs have become compelling alternatives to transformer-based models, which suffer from the quadratic computational and memory costs of attention mechanisms. As SSMs are increasingly deployed in real-world applications, it is critical to assess their susceptibility to both software- and hardware-level threats to ensure secure and reliable operation. Among such threats, hardware-induced bit-flip attacks (BFAs) pose a particularly severe risk by corrupting model parameters through memory faults, thereby undermining model accuracy and functional integrity. To investigate this vulnerability, we introduce RAMBO, the first BFA framework specifically designed to target Mamba-based architectures. Through experiments on the Mamba-1.4b model with LAMBADA benchmark, a cloze-style word-prediction task, we demonstrate that flipping merely a single critical bit can catastrophically reduce accuracy from 74.64% to 0% and increase perplexity from 18.94 to 3.75 x 10^6. These results demonstrate the pronounced fragility of SSMs to adversarial perturbations.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 15 of its 34 references that are in the map. First posted on arXiv 14 Dec 2025.
Builds on
15 of 34 references.
Closest ancestors · 2
Same direction, newest first
- 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality31 May
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spaces1 Dec
Other references · 13
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
- 2016The LAMBADA dataset: Word prediction requiring a broad discourse contextcited by 992
- 2016Practical Black-Box Attacks against Machine Learningcited by 903
- 2016Universal adversarial perturbationscited by 784
- 2019Hidden Trigger Backdoor Attackscited by 371
- 2024MambaVision: A Hybrid Mamba-Transformer Vision Backbonecited by 224
- 2019Bit-Flip Attack: Crushing Neural Network with Progressive Bit Searchcited by 108
- 2024A Survey of Resource-efficient LLM and Multimodal Foundation Modelscited by 86
- 2020DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flipscited by 56
- 2024Can Perplexity Reflect Large Language Model's Ability in Long Text Understanding?cited by 45
1 more
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025SpecMamba: Accelerating Mamba Inference on FPGA with Speculative Decoding
- 2024GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs
- 2024Bi-Mamba: Towards Accurate 1-Bit State Space Models
- 2025PerfMamba: Performance Analysis and Pruning of Selective State Space Models
- 2025Characterizing the Behavior of Training Mamba-based State Space Models on GPUs
- 2024PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips
- 2025SilentStriker:Toward Stealthy Bit-Flip Attacks on Large Language Models
- 2025Has the Two-Decade-Old Prophecy Come True? Artificial Bad Intelligence Triggered by Merely a Single-Bit Flip in Large Language Models