With the widespread adoption of open-source code language models (code LMs), intellectual property (IP) protection has become an increasingly critical concern.While current watermarking techniques have the potential to identify the code LM to protect its IP, they have limitations when facing the more practical and complex demand, i.e., offering the individual user-level tracing in the black-box setting.This work presents CLMTracing, a black-box code LM watermarking framework employing the rule-based watermarks and utility-preserving injection method for user-level model tracing.CLMTracing further incorporates a parameter selection algorithm sensitive to the robust watermark and adversarial training to enhance the robustness against watermark removal attacks.Comprehensive evaluations demonstrate CLM-Tracing is effective across multiple state-ofthe-art (SOTA) code LMs, showing significant harmless improvements compared to existing SOTA baselines and strong robustness against various removal attacks.

Rumors are widely spread on social media, which has a negative impact on social stability. To address this problem, many rumor detection methods have been proposed. However, most existing methods overlook the potential impact of noise and adversarial attacks on their detection performance, which could compromise their effectiveness when applied in an unknown environment. To overcome these challenges and improve the framework robustness to noise and adversarial attacks, we propose a novel rumor detection framework with Adaptive Data Augmentation and Adversarial Training, named ADAAT. Our framework utilizes the adaptive data augmentation module to calculate the importance of edges and features and adaptively modify the less important among them with a greater probability. In addition, it contains a hard sample generation module which generates adversarial representations through adversarial training. These adversarial representations are treated as hard samples, which are utilized in contrastive learning to learn essential features, thereby improving the robustness of the framework. Our framework proves superiority in rumor detection tasks, increasing the accuracy by an average of 3.6%, 4.5% and 2.5% over the state-of-the-art methods on Twitter15, Twitter16 and PHEME, respectively. When the ADAAT framework is applied to attacked test data, the detection accuracy decreases by only 1.3%, 1.4%, and 1.2%. This paper appears in the AI & Society Track.