The rapid advancements of large language models (LLMs) have raised public concerns about the privacy leakage of personally identifiable information (PII) within their extensive training datasets. Recent studies have demonstrated that an adversary could extract highly sensitive privacy data from the training data of LLMs with carefully designed prompts. However, these attacks suffer from the model's tendency to hallucinate and catastrophic forgetting (CF) in the pre-training stage, rendering the veracity of divulged PIIs negligible. In our research, we propose a novel attack, Janus, which exploits the fine-tuning interface to recover forgotten PIIs from the pre-training data in LLMs. We formalize the privacy leakage problem in LLMs and explain why forgotten PIIs can be recovered through empirical analysis on open-source language models. Based upon these insights, we evaluate the performance of Janus on both open-source language models and two latest LLMs, i.e., GPT-3.5-Turbo and LLaMA-2-7b. Our experiment results show that Janus amplifies the privacy risks by over 10 times in comparison with the baseline and significantly outperforms the state-of-the-art privacy extraction attacks including prefix attacks and in-context learning (ICL). Furthermore, our analysis validates that existing fine-tuning APIs provided by OpenAI and Azure AI Studio are susceptible to our Janus attack, allowing an adversary to conduct such an attack at a low cost.

Grasping and moving objects in a large cluster is a common real scenario. In such scenarios, tens of objects are adjacent to each other, even stacked layer by layer, so that simple grasp would not work due to obstruction. In this paper, we propose a well-designed strategy to use synergy of pushing and grasping to automatically push and grasp objects in a large tightly packed cluster of objects. Our strategy is to detect and grasp isolated graspable objects first before other actions. We then use a smart strategy that pushes objects at the narrowest edge of the clusters. For push action, the robot pushes the edge at the perpendicular direction relative to the cluster, thus improving the performance of isolation and minimizing collisions. We have conducted experiments in both simulation and real-world environments with more than 20 cluttered objects and demonstrated that our solution outperforms existing deep learning based methods, especially in challenging cases, and achieves significantly higher completion rate, grasp success rate, picked rate and efficiency.

In this paper, we propose a novel type-II hybrid ARQ scheme using low density parity check (LDPC) codes. The proposed approach combines low hardware overhead with good decoding performance by using an efficient decoder operating at a much higher rate with a much smaller size parity check matrix. Our scheme makes parts of the previously received data gradually improved until successful decoding of the entire original codeword. We also present a novel efficient framework for constructing rate-compatible LDPC codes applied in our hybrid ARQ scheme. The progressive edge growth (PEG) construction method with zigzag pattern results in linear-time encoding.