Yun Dong

Romina Omidi, Yun Dong, Binghui Wang

Google's SynthID-Text, the first ever production-ready generative watermark system for large language model, designs a novel Tournament-based method that achieves the state-of-the-art detectability for identifying AI-generated texts. The system's innovation lies in: 1) a new Tournament sampling algorithm for watermarking embedding, 2) a detection strategy based on the introduced score function (e.g., Bayesian or mean score), and 3) a unified design that supports both distortionary and non-distortionary watermarking methods. This paper presents the first theoretical analysis of SynthID-Text, with a focus on its detection performance and watermark robustness, complemented by empirical validation. For example, we prove that the mean score is inherently vulnerable to increased tournament layers, and design a layer inflation attack to break SynthID-Text. We also prove the Bayesian score offers improved watermark robustness w.r.t. layers and further establish that the optimal Bernoulli distribution for watermark detection is achieved when the parameter is set to 0.5. Together, these theoretical and empirical insights not only deepen our understanding of SynthID-Text, but also open new avenues for analyzing effective watermark removal strategies and designing robust watermarking techniques. Source code is available at https: //github.com/romidi80/Synth-ID-Empirical-Analysis.

Binghui Zhang, Sayedeh Leila Noorbakhsh, Yun Dong et al.

Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain task utility as well. Particularly, we propose an information-theoretic framework to achieve the goals through the lens of representation learning, i.e., learning representations that are robust to both adversarial examples and attribute inference adversaries. We also derive novel theoretical results under our framework, e.g., the inherent trade-off between adversarial robustness/utility and attribute privacy, and guaranteed attribute privacy leakage against attribute inference adversaries.

Jiate Li, Meng Pang, Yun Dong et al.

Graph neural networks (GNNs) are becoming the de facto method to learn on the graph data and have achieved the state-of-the-art on node and graph classification tasks. However, recent works show GNNs are vulnerable to training-time poisoning attacks -- marginally perturbing edges, nodes, or/and node features of training graph(s) can largely degrade GNNs' testing performance. Most previous defenses against graph poisoning attacks are empirical and are soon broken by adaptive / stronger ones. A few provable defenses provide robustness guarantees, but have large gaps when applied in practice: 1) restrict the attacker on only one type of perturbation; 2) design for a particular GNN architecture or task; and 3) robustness guarantees are not 100\% accurate. In this work, we bridge all these gaps by developing PGNNCert, the first certified defense of GNNs against poisoning attacks under arbitrary (edge, node, and node feature) perturbations with deterministic robustness guarantees. Extensive evaluations on multiple node and graph classification datasets and GNNs demonstrate the effectiveness of PGNNCert to provably defend against arbitrary poisoning perturbations. PGNNCert is also shown to significantly outperform the state-of-the-art certified defenses against edge perturbation or node perturbation during GNN training.

Jiate Li, Meng Pang, Yun Dong et al.

Explainable Graph Neural Network (GNN) has emerged recently to foster the trust of using GNNs. Existing GNN explainers are developed from various perspectives to enhance the explanation performance. We take the first step to study GNN explainers under adversarial attack--We found that an adversary slightly perturbing graph structure can ensure GNN model makes correct predictions, but the GNN explainer yields a drastically different explanation on the perturbed graph. Specifically, we first formulate the attack problem under a practical threat model (i.e., the adversary has limited knowledge about the GNN explainer and a restricted perturbation budget). We then design two methods (i.e., one is loss-based and the other is deduction-based) to realize the attack. We evaluate our attacks on various GNN explainers and the results show these explainers are fragile.