We target practical anonymization of Persian customer chats by training a compact NER model from LLM-labeled supervision and selecting the best labeler for deployment. We compare three instruction-tuned LLMs: DeepSeek-V3-0324, GPT-OSS-120B, and Qwen3-235B-A22B-Instruct-2507, to produce span annotations under a shared JSON protocol, yielding four corpora (OSS_ZeroShot, Qwen_ZeroShot, Qwen_FewShot, DeepSeek_FewShot). A MatinaRoberta-based token-classifier is trained per corpus and evaluated with token-level Precision/Recall/F1 (overall and per-class). We also report Label Coverage Recall (LCR), the proportion of gold non-O tokens predicted as non-O, and quantify cross-labeler behavior via a token-level Venn on test annotations. Finally, we contrast test-set annotation latency of the LLMs on H200 nodes with the trained NER's test-time labeling on a single RTX 3090. Results show that supervision from OSS_ZeroShot yields the strongest macro-F1 and LCR, while the resulting NER labels an entire 40K-message test set in approximately 2 minutes on one consumer GPU. This establishes a practical path to high-quality, low-cost anonymization for Persian industrial data.

Model extraction attacks exploit the target model’s prediction API to create a surrogate model, allowing the adversary to steal or reconnoiter the functionality of the target model in the black-box setting. Several recent studies have shown that a data-limited adversaries with no or limited access to the samples from the target model’s training data distribution, can employ synthesized or semantically similar samples to conduct model extraction attacks. In this paper, we introduce the concept of hardness degree to characterize sample difficulty based on the concept of learning speed. The hardness degree of a sample depends on the epoch number at which the predicted label for that sample converges. We investigate the hardness degree of samples and demonstrate that the hardness degree histogram of a data-limited adversary’s sample sequence is differs significantly from that of benign users’ sample sequences. We propose Hardness-Oriented Detection Approach (HODA) to detect the sample sequences of model extraction attacks. Our results indicate that HODA can effectively detect model extraction attack sequences with a high success rate, using only 100 monitored samples. It outperforms all previously proposed methods for model extraction detection.

Network traffic classification is used in various applications such as network traffic management, policy enforcement, and intrusion detection systems. Although most applications encrypt their network traffic and some of them dynamically change their port numbers, Machine Learning (ML) and especially Deep Learning (DL)-based classifiers have shown impressive performance in network traffic classification. In this article, we evaluate the robustness of DL-based network traffic classifiers against Adversarial Network Traffic (ANT). ANT causes DL-based network traffic classifiers to predict incorrectly using Universal Adversarial Perturbation (UAP) generating methods. Since there is no need to buffer network traffic before sending ANT, it is generated live. We partition the input space of the DL-based network traffic classification into three categories: packet classification, flow content classification, and flow time series classification. To generate ANT, we propose three new attacks injecting UAP into network traffic. AdvPad attack injects a UAP into the content of packets to evaluate the robustness of packet classifiers. AdvPay attack injects a UAP into the payload of a dummy packet to evaluate the robustness of flow content classifiers. AdvBurst attack injects a specific number of dummy packets with crafted statistical features based on a UAP into a selected burst of a flow to evaluate the robustness of flow time series classifiers. The results indicate injecting a little UAP into network traffic, highly decreases the performance of DL-based network traffic classifiers in all categories.