When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning

Federated Ranking Learning (FRL) is a state-of-the-art FL framework that stands out for its communication efficiency and resilience to poisoning attacks. It diverges from the traditional FL framework in two ways: 1) it leverages discrete rankings instead of gradient updates, significantly reducing communication costs and limiting the potential space for malicious updates, and 2) it uses majority voting on the server side to establish the global ranking, ensuring that individual updates have minimal influence since each client contributes only a single vote. These features enhance the system's scalability and position FRL as a promising paradigm for FL training. However, our analysis reveals that FRL is not inherently robust, as certain edges are particularly vulnerable to poisoning attacks. Through a theoretical investigation, we prove the existence of these vulnerable edges and establish a lower bound and an upper bound for identifying them in each layer. Based on this finding, we introduce a novel local model poisoning attack against FRL, namely Vulnerable Edge Manipulation (VEM) attack. The VEM attack focuses on identifying and perturbing the most vulnerable edges in each layer and leveraging an optimization-based approach to maximize the attack's impact. Through extensive experiments on benchmark datasets, we demonstrate that our attack achieves an overall 53.23 % attack impact and is 3.7× more impactful than existing methods. Our findings highlight significant vulnerabilities in ranking-based FL systems and underline the urgency for the development of new robust FL frameworks.

The Large Language Model (LLM) watermark is a newly emerging technique that shows promise in addressing concerns surrounding LLM copyright, monitoring AI-generated text, and preventing its misuse. The LLM watermark scheme commonly includes generating secret keys to partition the vocabulary into green and red lists, applying a perturbation to the logits of tokens in the green list to increase their sampling likelihood, thus facilitating watermark detection to identify AI-generated text if the proportion of green tokens exceeds a threshold. However, recent research indicates that watermarking methods using numerous keys are susceptible to removal attacks, such as token editing, synonym substitution, and paraphrasing, with robustness declining as the number of keys increases. Therefore, the state-of-the-art watermark schemes that employ fewer or single keys have been demonstrated to be more robust against text editing and paraphrasing. In this paper, we propose a novel green list stealing attack against the state-of-the-art LLM watermark scheme and systematically examine its vulnerability to this attack. We formalize the attack as a mixed integer programming problem with constraints. We evaluate our attack under a comprehensive threat model, including an extreme scenario where the attacker has no prior knowledge, lacks access to the watermark detector API, and possesses no information about the LLM’s parameter settings or watermark injection/detection scheme. Extensive experiments on LLMs, such as OPT and LLaMA, demonstrate that our attack can successfully steal the green list and remove the watermark across all settings.

Adversarial attacks are a serious threat to the reliable deployment of machine learning models in safety-critical applications. They can misguide current models to predict incorrectly by slightly modifying the inputs. Recently, substantial work has shown that adversarial examples tend to deviate from the underlying data manifold of normal examples, whereas pre-trained masked language models can fit the manifold of normal NLP data. To explore how to use the masked language model in adversarial detection, we propose a novel textual adversarial example detection method, namely Masked Language Model-based Detection (MLMD), which can produce clearly distinguishable signals between normal examples and adversarial examples by exploring the changes in manifolds induced by the masked language model. MLMD features a plug and play usage (i.e., no need to retrain the victim model) for adversarial defense and it is agnostic to classification tasks, victim model’s architectures, and to-be-defended attack methods. We evaluate MLMD on various benchmark textual datasets, widely studied machine learning models, and state-of-the-art (SOTA) adversarial attacks (in total 3*4*4 = 48 settings). Experimental results show that MLMD can achieve strong performance, with detection accuracy up to 0.984, 0.967, and 0.901 on AG-NEWS, IMDB, and SST-2 datasets, respectively. Additionally, MLMD is superior, or at least comparable to, the SOTA detection defenses in detection accuracy and F1 score. Among many defenses based on the off-manifold assumption of adversarial examples, this work offers a new angle for capturing the manifold change. The code for this work is openly accessible at https://github.com/mlmddetection/MLMDdetection.

Deep learning models are known to be vulnerable to adversarial examples that are elaborately designed for malicious purposes and are imperceptible to the human perceptual system. Autoencoder, when trained solely over benign examples, has been widely used for (self-supervised) adversarial detection based on the assumption that adversarial examples yield larger reconstruction errors. However, because lacking adversarial examples in its training and the too strong generalization ability of autoencoder, this assumption does not always hold true in practice. To alleviate this problem, we explore how to detect adversarial examples with disentangled label/semantic features under the autoencoder structure. Specifically, we propose Disentangled Representation-based Reconstruction (DRR). In DRR, we train an autoencoder over both correctly paired label/semantic features and incorrectly paired label/semantic features to reconstruct benign and counterexamples. This mimics the behavior of adversarial examples and can reduce the unnecessary generalization ability of autoencoder. We compare our method with the state-of-the-art self-supervised detection methods under different adversarial attacks and different victim models, and it exhibits better performance in various metrics (area under the ROC curve, true positive rate, and true negative rate) for most attack settings. Though DRR is initially designed for visual tasks only, we demonstrate that it can be easily extended for natural language tasks as well. Notably, different from other autoencoder-based detectors, our method can provide resistance to the adaptive adversary.

Abstract The usage of deep learning is being escalated in many applications. Due to its outstanding performance, it is being used in a variety of security and privacy-sensitive areas in addition to conventional applications. One of the key aspects of deep learning efficacy is to have abundant data. This trait leads to the usage of data which can be highly sensitive and private, which in turn causes wariness with regard to deep learning in the general public. Membership inference attacks are considered lethal as they can be used to figure out whether a piece of data belongs to the training dataset or not. This can be problematic with regard to leakage of training data information and its characteristics. To highlight the significance of these types of attacks, we propose an enhanced methodology for membership inference attacks based on adversarial robustness, by adjusting the directions of adversarial perturbations through label smoothing under a white-box setting. We evaluate our proposed method on three datasets: Fashion-MNIST, CIFAR-10 and CIFAR-100. Our experimental results reveal that the performance of our method surpasses that of the existing adversarial robustness-based method when attacking normally trained models. Additionally, through comparing our technique with the state-of-the-art metric-based membership inference methods, our proposed method also shows better performance when attacking adversarially trained models. The code for reproducing the results of this work is available at https://github.com/plll4zzx/Evaluating-Membership-Inference-Through-Adversarial-Robustness.