Search

Model extraction aims to create a functionally similar copy from a machine learning as a service (MLaaS) API with minimal overhead, typically for illicit profit or as a precursor to further attacks, posing a significant threat to the MLaaS ecosystem. However, recent studies have shown that model extraction is highly inefficient, particularly when the target task distribution is unavailable. In such cases, even substantially increasing the attack budget fails to produce a sufficiently similar replica, reducing the adversary's motivation to pursue extraction attacks. In this paper, we revisit the elementary design choices throughout the extraction lifecycle. We propose an embarrassingly simple yet dramatically effective algorithm, Efficient and Effective Model Extraction (E3), focusing on both query preparation and training routine. E3 achieves superior generalization compared to state-of-the-art methods while minimizing computational costs. For instance, with only 0.005 times the query budget and less than 0.2 times the runtime, E3 outperforms classical generative model based data-free model extraction by an absolute accuracy improvement of over 50% on CIFAR-10. Our findings underscore the persistent threat posed by model extraction and suggest that it could serve as a valuable benchmarking algorithm for future security evaluations.

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and effective strategy for preventing unauthorized model distribution. However, this paper identifies an inherent flaw in the current paradigm of trigger set watermarking: evasion adversaries can readily exploit the shortcuts created by models memorizing watermark samples that deviate from the main task distribution, significantly impairing their generalization in adversarial settings. To counteract this, we leverage diffusion models to synthesize unrestricted adversarial examples as trigger sets. By learning the model to accurately recognize them, unique watermark behaviors are promoted through knowledge injection rather than error memorization, thus avoiding exploitable shortcuts. Furthermore, we uncover that the resistance of current trigger set watermarking against removal attacks primarily relies on significantly damaging the decision boundaries during embedding, intertwining unremovability with adverse impacts. By optimizing the knowledge transfer properties of protected models, our approach conveys watermark behaviors to extraction surrogates without aggressively decision boundary perturbation. Experimental results on CIFAR-10/100 and Imagenette datasets demonstrate the effectiveness of our method, showing not only improved robustness against evasion adversaries but also superior resistance to watermark removal attacks compared to state-of-the-art solutions.

Generative models have shown a giant leap in synthesizing photo-realistic images with minimal expertise, sparking concerns about the authenticity of online information. This study aims to develop a universal AI-generated image detector capable of identifying images from diverse sources. Existing methods struggle to generalize across unseen generative models when provided with limited sample sources. Inspired by the zero-shot transferability of pre-trained vision-language models, we seek to harness the nontrivial visual-world knowledge and descriptive proficiency of CLIP-ViT to generalize over unknown domains. This paper presents a novel parameter-efficient fine-tuning approach, mixture of low-rank experts, to fully exploit CLIP-ViT's potential while preserving knowledge and expanding capacity for transferable detection. We adapt only the MLP layers of deeper ViT blocks via an integration of shared and separate LoRAs within an MoE-based structure. Extensive experiments on public benchmarks show that our method achieves superiority over state-of-the-art approaches in cross-generator generalization and robustness to perturbations. Remarkably, our best-performing ViT-L/14 variant requires training only 0.08% of its parameters to surpass the leading baseline by +3.64% mAP and +12.72% avg.Acc across unseen diffusion and autoregressive models. This even outperforms the baseline with just 0.28% of the training data. Our code and pre-trained models will be available at https://github.com/zhliuworks/CLIPMoLE.

To trace the copyright of deep neural networks, an owner can embed its identity information into its model as a watermark. The capacity of the watermark quantify the maximal volume of information that can be verified from the watermarked model. Current studies on capacity focus on the ownership verification accuracy under ordinary removal attacks and fail to capture the relationship between robustness and fidelity. This paper studies the capacity of deep neural network watermarks from an information theoretical perspective. We propose a new definition of deep neural network watermark capacity analogous to channel capacity, analyze its properties, and design an algorithm that yields a tight estimation of its upper bound under adversarial overwriting. We also propose a universal non-invasive method to secure the transmission of the identity message beyond capacity by multiple rounds of ownership verification. Our observations provide evidence for neural network owners and defenders that are curious about the tradeoff between the integrity of their ownership and the performance degradation of their products., Comment: Accepted by AAAI 2024

As ultra-realistic face forgery techniques emerge, deepfake detection has attracted increasing attention due to security concerns. Many detectors cannot achieve accurate results when detecting unseen manipulations despite excellent performance on known forgeries. In this paper, we are motivated by the observation that the discrepancies between real and fake videos are extremely subtle and localized, and inconsistencies or irregularities can exist in some critical facial regions across various information domains. To this end, we propose a novel pipeline, Cross-Domain Local Forensics (XDLF), for more general deepfake video detection. In the proposed pipeline, a specialized framework is presented to simultaneously exploit local forgery patterns from space, frequency, and time domains, thus learning cross-domain features to detect forgeries. Moreover, the framework leverages four high-level forgery-sensitive local regions of a human face to guide the model to enhance subtle artifacts and localize potential anomalies. Extensive experiments on several benchmark datasets demonstrate the impressive performance of our method, and we achieve superiority over several state-of-the-art methods on cross-dataset generalization. We also examined the factors that contribute to its performance through ablations, which suggests that exploiting cross-domain local characteristics is a noteworthy direction for developing more general deepfake detectors.

Backdoor-based watermarking schemes were proposed to protect the intellectual property of artificial intelligence models, especially deep neural networks, under the black-box setting. Compared with ordinary backdoors, backdoor-based watermarks need to digitally incorporate the owner's identity, which fact adds extra requirements to the trigger generation and verification programs. Moreover, these concerns produce additional security risks after the watermarking scheme has been published for as a forensics tool or the owner's evidence has been eavesdropped on. This paper proposes the capsulation attack, an efficient method that can invalidate most established backdoor-based watermarking schemes without sacrificing the pirated model's functionality. By encapsulating the deep neural network with a rule-based or Bayes filter, an adversary can block ownership probing and reject the ownership verification. We propose a metric, CAScore, to measure a backdoor-based watermarking scheme's security against the capsulation attack. This paper also proposes a new backdoor-based deep neural network watermarking scheme that is secure against the capsulation attack by reversing the encoding process and randomizing the exposure of triggers.

Neural table-to-text generation approaches are data-hungry, limiting their adaptation for low-resource real-world applications. Previous works mostly resort to Pre-trained Language Models (PLMs) to generate fluent summaries of a table. However, they often contain hallucinated contents due to the uncontrolled nature of PLMs. Moreover, the topological differences between tables and sequences are rarely studied. Last but not least, fine-tuning on PLMs with a handful of instances may lead to over-fitting and catastrophic forgetting. To alleviate these problems, we propose a prompt-based approach, Prefix-Controlled Generator (i.e., PCG), for few-shot table-to-text generation. We prepend a task-specific prefix for a PLM to make the table structure better fit the pre-trained input. In addition, we generate an input-specific prefix to control the factual contents and word order of the generated text. Both automatic and human evaluations on different domains (humans, books and songs) of the Wikibio dataset show substantial improvements over baseline approaches., Comment: Accpeted by COLING 2022 as a long paper

Watermarking has become a plausible candidate for ownership verification and intellectual property protection of deep neural networks. Regarding image classification neural networks, current watermarking schemes uniformly resort to backdoor triggers. However, injecting a backdoor into a neural network requires knowledge of the training dataset, which is usually unavailable in the real-world commercialization. Meanwhile, established watermarking schemes oversight the potential damage of exposed evidence during ownership verification and the watermarking algorithms themselves. Those concerns decline current watermarking schemes from industrial applications. To confront these challenges, we propose a knowledge-free black-box watermarking scheme for image classification neural networks. The image generator obtained from a data-free distillation process is leveraged to stabilize the network's performance during the backdoor injection. A delicate encoding and verification protocol is designed to ensure the scheme's security against knowledgable adversaries. We also give a pioneering analysis of the capacity of the watermarking scheme. Experiment results proved the functionality-preserving capability and security of the proposed watermarking scheme., Comment: 11 pages

Deep neural networks are playing an important role in many real-life applications. After being trained with abundant data and computing resources, a deep neural network model providing service is endowed with economic value. An important prerequisite in commercializing and protecting deep neural networks is the reliable identification of their genuine author. To meet this goal, watermarking schemes that embed the author's identity information into the networks have been proposed. However, current schemes can hardly meet all the necessary requirements for securely proving the authorship and mostly focus on models for classification. To explicitly meet the formal definitions of the security requirements and increase the applicability of deep neural network watermarking schemes, we propose a new framework based on multi-task learning. By treating the watermark embedding as an extra task, most of the security requirements are explicitly formulated and met with well-designed regularizers, the rest is guaranteed by using components from cryptography. Moreover, a decentralized verification protocol is proposed to standardize the ownership verification. The experiment results show that the proposed scheme is flexible, secure, and robust, hence a promising candidate in deep learning model protection., Comment: The updated version of this manuscript would appear in the AAAI-2022 Workshop on Artificial Intelligence Safety (SafeAI)