Optimizing Adaptive Attacks against Content Watermarks for Language Models

Large Language Models (LLMs) can be \emph{misused} to spread online spam and misinformation. Content watermarking deters misuse by hiding a message in model-generated outputs, enabling their detection using a secret watermarking key. Robustness is a core security property, stating that evading detection requires (significant) degradation of the content's quality. Many LLM watermarking methods have been proposed, but robustness is tested only against \emph{non-adaptive} attackers who lack knowledge of the watermarking method and can find only suboptimal attacks. We formulate the robustness of LLM watermarking as an objective function and propose preference-based optimization to tune \emph{adaptive} attacks against the specific watermarking method. Our evaluation shows that (i) adaptive attacks substantially outperform non-adaptive baselines. (ii) Even in a non-adaptive setting, adaptive attacks optimized against a few known watermarks remain highly effective when tested against other unseen watermarks, and (iii) optimization-based attacks are practical and require less than seven GPU hours. Our findings underscore the need to test robustness against adaptive attackers.

Universal Backdoor Attacks

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike adversarial examples, backdoor attacks often target specific classes rather than any class learned by the model. One might expect that targeting many classes through a naive composition of attacks vastly increases the number of poison samples. We show this is not necessarily true and more efficient, universal data poisoning attacks exist that allow controlling misclassifications from any source class into any target class with a small increase in poison samples. Our idea is to generate triggers with salient characteristics that the model can learn. The triggers we craft exploit a phenomenon we call inter-class poison transferability, where learning a trigger from one class makes the model more vulnerable to learning triggers for other classes. We demonstrate the effectiveness and robustness of our universal backdoor attacks by controlling models with up to 6,000 classes while poisoning only 0.15% of the training dataset.

Leveraging Optimization for Adaptive Attacks on Image Watermarks

Untrustworthy users can misuse image generators to synthesize high-quality deepfakes and engage in online spam or disinformation campaigns. Watermarking deters misuse by marking generated content with a hidden message, enabling its detection using a secret watermarking key. A core security property of watermarking is robustness, which states that an attacker can only evade detection by substantially degrading image quality. Assessing robustness requires designing an adaptive attack for the specific watermarking algorithm. A challenge when evaluating watermarking algorithms and their (adaptive) attacks is to determine whether an adaptive attack is optimal, i.e., it is the best possible attack. We solve this problem by defining an objective function and then approach adaptive attacks as an optimization problem. The core idea of our adaptive attacks is to replicate secret watermarking keys locally by creating surrogate keys that are differentiable and can be used to optimize the attack's parameters. We demonstrate for Stable Diffusion models that such an attacker can break all five surveyed watermarking methods at negligible degradation in image quality. These findings emphasize the need for more rigorous robustness testing against adaptive, learnable attackers.

Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions

Machine Learning as a Service (MLaaS) is an increasingly popular design where a company with abundant computing resources trains a deep neural network and offers query access for tasks like image classification. The challenge with this design is that MLaaS requires the client to reveal their potentially sensitive queries to the company hosting the model. Multi-party computation (MPC) protects the client's data by allowing encrypted inferences. However, current approaches suffer prohibitively large inference times. The inference time bottleneck in MPC is the evaluation of non-linear layers such as ReLU activation functions. Motivated by the success of previous work co-designing machine learning and MPC aspects, we develop an activation function co-design. We replace all ReLUs with a polynomial approximation and evaluate them with single-round MPC protocols, which give state-of-the-art inference times in wide-area networks. Furthermore, to address the accuracy issues previously encountered with polynomial activations, we propose a novel training algorithm that gives accuracy competitive with plaintext models. Our evaluation shows between $4$ and $90\times$ speedups in inference time on large models with up to $23$ million parameters while maintaining competitive inference accuracy.

Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks against Deep Image Classification

Deep image classification models trained on large amounts of web-scraped data are vulnerable to data poisoning, a mechanism for backdooring models. Even a few poisoned samples seen during training can entirely undermine the model's integrity during inference. While it is known that poisoning more samples enhances an attack's effectiveness and robustness, it is unknown whether poisoning too many samples weakens an attack by making it more detectable. We observe a fundamental detectability/robustness trade-off in data poisoning attacks: Poisoning too few samples renders an attack ineffective and not robust, but poisoning too many samples makes it detectable. This raises the bar for data poisoning attackers who have to balance this trade-off to remain robust and undetectable. Our work proposes two defenses designed to (i) detect and (ii) repair poisoned models as a post-processing step after training using a limited amount of trusted image-label pairs. We show that our defenses mitigate all surveyed attacks and outperform existing defenses using less trusted data to repair a model. Our defense scales to joint vision-language models, such as CLIP, and interestingly, we find that attacks on larger models are more easily detectable but also more robust than those on smaller models. Lastly, we propose two adaptive attacks demonstrating that while our work raises the bar for data poisoning attacks, it cannot mitigate all forms of backdooring.

PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators

Deepfakes refer to content synthesized using deep generators, which, when \emph{misused}, have the potential to erode trust in digital media. Synthesizing high-quality deepfakes requires access to large and complex generators only few entities can train and provide. The threat are malicious users that exploit access to the provided model and generate harmful deepfakes without risking detection. Watermarking makes deepfakes detectable by embedding an identifiable code into the generator that is later extractable from its generated images. We propose Pivotal Tuning Watermarking (PTW), a method for watermarking pre-trained generators (i) three orders of magnitude faster than watermarking from scratch and (ii) without the need for any training data. We improve existing watermarking methods and scale to generators $4 \times$ larger than related work. PTW can embed longer codes than existing methods while better preserving the generator's image quality. We propose rigorous, game-based definitions for robustness and undetectability and our study reveals that watermarking is not robust against an adaptive white-box attacker who has control over the generator's parameters. We propose an adaptive attack that can successfully remove any watermarking with access to only $200$ non-watermarked images. Our work challenges the trustworthiness of watermarking for deepfake detection when the parameters of a generator are available.

Analyzing Leakage of Personally Identifiable Information in Language Models

Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs leaking Personally Identifiable Information (PII) has received less attention, which can be attributed to the false assumption that dataset curation techniques such as scrubbing are sufficient to prevent PII leakage. Scrubbing techniques reduce but do not prevent the risk of PII leakage: in practice scrubbing is imperfect and must balance the trade-off between minimizing disclosure and preserving the utility of the dataset. On the other hand, it is unclear to which extent algorithmic defenses such as differential privacy, designed to guarantee sentence- or user-level privacy, prevent PII disclosure. In this work, we propose (i) a taxonomy of PII leakage in LMs, (ii) metrics to quantify PII leakage, and (iii) attacks showing that PII leakage is a threat in practice. Our taxonomy provides rigorous game-based definitions for PII leakage via black-box extraction, inference, and reconstruction attacks with only API access to an LM. We empirically evaluate attacks against GPT-2 models fine-tuned on three domains: case law, health care, and e-mails. Our main contributions are (i) novel attacks that can extract up to 10 times more PII sequences as existing attacks, (ii) showing that sentence-level differential privacy reduces the risk of PII disclosure but still leaks about 3% of PII sequences, and (iii) a subtle connection between record-level membership inference and PII reconstruction.

SoK: How Robust is Image Classification Deep Neural Network Watermarking?

Deep Neural Network (DNN) watermarking is a method for provenance verification of DNN models. Watermarking should be robust against watermark removal attacks that derive a surrogate model that evades provenance verification. Many watermarking schemes that claim robustness have been proposed, but their robustness is only validated in isolation against a relatively small set of attacks. There is no systematic, empirical evaluation of these claims against a common, comprehensive set of removal attacks. This uncertainty about a watermarking scheme's robustness causes difficulty to trust their deployment in practice. In this paper, we evaluate whether recently proposed watermarking schemes that claim robustness are robust against a large set of removal attacks. We survey methods from the literature that (i) are known removal attacks, (ii) derive surrogate models but have not been evaluated as removal attacks, and (iii) novel removal attacks. Weight shifting and smooth retraining are novel removal attacks adapted to the DNN watermarking schemes surveyed in this paper. We propose taxonomies for watermarking schemes and removal attacks. Our empirical evaluation includes an ablation study over sets of parameters for each attack and watermarking scheme on the CIFAR-10 and ImageNet datasets. Surprisingly, none of the surveyed watermarking schemes is robust in practice. We find that schemes fail to withstand adaptive attacks and known methods for deriving surrogate models that have not been evaluated as removal attacks. This points to intrinsic flaws in how robustness is currently evaluated. We show that watermarking schemes need to be evaluated against a more extensive set of removal attacks with a more realistic adversary model. Our source code and a complete dataset of evaluation results are publicly available, which allows to independently verify our conclusions.

Deep Neural Network Fingerprinting by Conferrable Adversarial Examples

In Machine Learning as a Service, a provider trains a deep neural network and provides many users access to it. However, the hosted (source) model is susceptible to model stealing attacks where an adversary derives a \emph{surrogate model} from API access to the source model. For post hoc detection of such attacks, the provider needs a robust method to determine whether a suspect model is a surrogate of their model or not. We propose a fingerprinting method for deep neural networks that extracts a set of inputs from the source model so that only surrogates agree with the source model on the classification of such inputs. These inputs are a specifically crafted subclass of targeted transferable adversarial examples which we call conferrable adversarial examples that transfer exclusively from a source model to its surrogates. We propose new methods to generate these conferrable adversarial examples and use them as our fingerprint. Our fingerprint is the first to be successfully tested as robust against distillation attacks, and our experiments show that this robustness extends to robustness against weaker removal attacks such as fine-tuning, ensemble attacks, and adversarial retraining. We even protect against a powerful adversary with white-box access to the source model, whereas the defender only needs black-box access to the surrogate model. We conduct our experiments on the CINIC dataset and a subset of ImageNet32 with 100 classes.

On the Robustness of the Backdoor-based Watermarking in Deep Neural Networks

Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized re-distribution, watermarking approaches have been introduced in the past couple of years. The watermark allows the legitimate owner to detect copyright violations of their model. We investigate the robustness and reliability of state-of-the-art deep neural network watermarking schemes. We focus on backdoor-based watermarking and show that an adversary can remove the watermark fully by just relying on public data and without any access to the model's sensitive information such as the training data set, the trigger set or the model parameters. We as well prove the security inadequacy of the backdoor-based watermarking in keeping the watermark hidden by proposing an attack that detects whether a model contains a watermark.