mlsanityData to 14 Oct 2026

LLA: Enhancing Security and Privacy for Generative Models with Logic-Locked Accelerators

arXiv 2512.22307 ↗First posted 26 Dec 2025cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce LLA, an effective intellectual property (IP) protection scheme for generative AI models. LLA leverages the synergy between hardware and software to defend against various supply chain threats, including model theft, model corruption, and information leakage. On the software side, it embeds key bits into neurons that can trigger outliers to degrade performance and applies invariance transformations to obscure the key values. On the hardware side, it integrates a lightweight locking module into the AI accelerator while maintaining compatibility with various dataflow patterns and toolchains. An accelerator with a pre-stored secret key acts as a license to access the model services provided by the IP owner. The evaluation results show that LLA can withstand a broad range of oracle-guided key optimization attacks, while incurring a minimal computational overhead of less than 0.1% for 7,168 key bits.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 43 references that are in the map. First posted on arXiv 26 Dec 2025.

Builds on

15 of 43 references.

References · 15

  1. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  2. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 634
  3. 2024SliceGPT: Compress Large Language Models by Deleting Rows and Columnscited by 385
  4. 2024ShortGPT: Layers in Large Language Models are More Redundant Than You Expectcited by 383
  5. 2024QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebookscited by 378
  6. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  7. 2024DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMscited by 167
  8. 2023Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsitycited by 165
  9. 2024Compact Language Models via Pruning and Knowledge Distillationcited by 148
  10. 2022The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformerscited by 122
  11. 2021BERT Busters: Outlier Dimensions that Disrupt Transformerscited by 112
  12. 2023Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Modelscited by 94
3 more
  1. 2023A Pilot Study of Query-Free Adversarial Attack against Stable Diffusioncited by 76
  2. 2023NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscationcited by 16
  3. 2018LUT-Lock: A Novel LUT-based Logic Obfuscation for FPGA-Bitstream and ASIC-Hardware Protectioncited by 3

Built on by

Not cited yet.