An official website of the United States government
Recent advances in model piracy have uncovered a new security hole for malicious attacks endangering the Intellectual Property (IP) of Deep Learning (DL) systems. This manuscript features our research titled “DeepAttest: An End-toEnd Attestation Framework for Deep Neural Networks” [1] that is selected for the 2021 Top Picks in hardware and embedded security. DeepAttest is the first end-to-end framework that achieves reliable and efficient IP protection of DL devices with hardware-bounded usage control. We leverage device-specific model fingerprinting and Trusted Execution Environment (TEE) to ensure that only DL models with the device-specific fingerprint can run inference on protected hardware
more »
« less
This content will become publicly available on March 17, 2027
iSeal: Encrypted Fingerprinting for Reliable LLM Ownership Verification
Given the high cost of large language model (LLM) training from scratch, safeguarding LLM intellectual property (IP) becomes increasingly crucial. As the standard paradigm for IP ownership verification, LLM fingerprinting thus plays a vital role in addressing this challenge. Existing LLM fingerprinting methods verify ownership by extracting or injecting model-specific features. However, they overlook potential attacks during the verification process, leaving them ineffective when the model thief fully controls the LLM's inference process. In such settings, attackers may share prompt-response pairs to enable fingerprint unlearning, or manipulate outputs to evade exact-match verification. We propose iSeal, the first fingerprinting method designed for reliable verification when the model thief controls the suspected LLM in an end-to-end manner. It injects unique features into both the model and an external module, reinforced by an error-correction mechanism and a similarity-based verification strategy. These components are resistant to verification-time attacks, including collusion-based fingerprint unlearning and response manipulation, backed by both theoretical analysis and empirical results. iSeal achieves 100% Fingerprint Success Rate (FSR) on 12 LLMs against more than 10 attacks, while baselines fail under unlearning and response manipulations.
more »
« less
- Award ID(s):
- 2332638
- PAR ID:
- 10696980
- Publisher / Repository:
- AAAI
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 40
- Issue:
- 42
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 35940 to 35948
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Graph Neural Networks (GNNs) have emerged as powerful tools for processing graph-structured data, enabling applications in various domains. Yet, GNNs are vulnerable to model extraction attacks, imposing risks to intellectual property. To mitigate model extraction attacks, model ownership verification is considered an effective method. However, throughout a series of empirical studies, we found that the existing GNN ownership verification methods either mandate unrealistic conditions or present unsatisfactory accuracy under the most practical settings—the black-box setting where the verifier only requires access to the final output (e.g., posterior probability) of the target model and the suspect model. Inspired by the studies, we propose a new, black-box GNN ownership verification method that involves local independent models and shadow surrogate models to train a classifier for performing ownership verification. Our method boosts the verification accuracy by exploiting two insights: (1) We consider the overall behaviors of the target model for decision-making, better utilizing its holistic fingerprinting; (2) We enrich the fingerprinting of the target model by masking a subset of features of its training data, injecting extra information to facilitate ownership verification. To assess the effectiveness of our proposed method, we perform an intensive series of evaluations with 5 popular datasets, 5 mainstream GNN architectures, and 16 different settings. Our method achieves nearly perfect accuracy with a marginal impact on the target model in all cases, significantly outperforming the existing methods and enlarging their practicality. We also demonstrate that our method maintains robustness against adversarial attempts to evade the verification.more » « less
-
Graph Neural Networks (GNNs) have emerged as powerful tools for processing graph-structured data, enabling applications in various domains. Yet, GNNs are vulnerable to model extraction attacks, imposing risks to intellectual property. To mitigate model extraction attacks, model ownership verification is considered an effective method. However, throughout a series of empirical studies, we found that the existing GNN ownership verification methods either mandate unrealistic conditions or present unsatisfactory accuracy under the most practical settings—the black-box setting where the verifier only requires access to the final output (e.g., posterior probability) of the target model and the suspect model. Inspired by the studies, we propose a new, black-box GNN ownership verification method that involves local independent models and shadow surrogate models to train a classifier for performing ownership verification. Our method boosts the verification accuracy by exploiting two insights: (1) We consider the overall behaviors of the target model for decision-making, better utilizing its holistic fingerprinting; (2) We enrich the fingerprinting of the target model by masking a subset of features of its training data, injecting extra information to facilitate ownership verification. To assess the effectiveness of our proposed method, we perform an intensive series of evaluations with 5 popular datasets, 5 mainstream GNN architectures, and 16 different settings. Our method achieves nearly perfect accuracy with a marginal impact on the target model in all cases, significantly outperforming the existing methods and enlarging their practicality. We also demonstrate that our method maintains robustness against adversarial attempts to evade the verification.more » « less
-
Perumalla, Kalyan; Lopez Jr., Juan; Siraj, Ambareen (Ed.)Executable steganography, the hiding of software machine code inside of a larger program, is a potential approach to introduce new software protection constructs such as watermarks or fingerprints. Software fingerprinting is, therefore, a process similar to steganography, hiding data within other data. The goal of fingerprinting is to hide a unique secret message, such as a serial number, into copies of an executable program in order to provide proof of ownership of that program. Fingerprints are a special case of watermarks, with the difference being that each fingerprint is unique to each copy of a program. Traditionally, researchers describe four aims that a software fingerprint should achieve. These include the fingerprint should be difficult to remove, it should not be obvious, it should have a low false positive rate, and it should have negligible impact on performance. In this research, we propose to extend these objectives and introduce a fifth aim: that software fingerprints should be machine independent. As a result, the same fingerprinting method can be used regardless of the architecture used to execute the program. Hence, this paper presents an approach towards the realization of machine-independent fingerprinting of executable programs. We make use of Low-Level Virtual Machine (LLVM) intermediate representation during the software compilation process to demonstrate both a simple static fingerprinting method as well as a dynamic method, which displays our aim of hardware independent fingerprinting. The research contribution includes a realization of the approach using the LLVM infrastructure and provides a proof of concept for both simple static and dynamic watermarks that are architecture neutral.more » « less
-
In response to recent data regulation requirements, machine unlearning (MU) has emerged as a critical process to remove the influence of specific examples from a given model. Although exact unlearning can be achieved through complete model retraining using the remaining dataset, the associated computational costs have driven the development of efficient, approximate unlearning techniques. Moving beyond data-centric MU approaches, our study introduces a novel model-based perspective: model sparsification via weight pruning, which is capable of reducing the gap between exact unlearning and approximate unlearning. We show in both theory and practice that model sparsity can boost the multi-criteria unlearning performance of an approximate unlearner, closing the approximation gap, while continuing to be efficient. This leads to a new MU paradigm, termed prune first, then unlearn, which infuses a sparse model prior into the unlearning process. Building on this insight, we also develop a sparsity-aware unlearning method that utilizes sparsity regularization to enhance the training process of approximate unlearning. Extensive experiments show that our proposals consistently benefit MU in various unlearning scenarios. A notable highlight is the 77% unlearning efficacy gain of fine-tuning (one of the simplest unlearning methods) when using sparsity-aware unlearning. Furthermore, we demonstrate the practical impact of our proposed MU methods in addressing other machine learning challenges, such as defending against backdoor attacks and enhancing transfer learning. Codes are available at this https URL.more » « less
