Jinjing Zhao

Yuhui Li, Fangyun Wei, Jinjing Zhao et al.

Large language models (LLMs) often demonstrate inconsistencies with human preferences. Previous research typically gathered human preference data and then aligned the pre-trained models using reinforcement learning or instruction tuning, a.k.a. the finetuning step. In contrast, aligning frozen LLMs without requiring alignment data is more appealing. This work explores the potential of the latter setting. We discover that by integrating self-evaluation and rewind mechanisms, unaligned LLMs can directly produce responses consistent with human preferences via self-boosting. We introduce a novel inference method, Rewindable Auto-regressive INference (RAIN), that allows pre-trained LLMs to evaluate their own generation and use the evaluation results to guide rewind and generation for AI safety. Notably, RAIN operates without the need of extra data for model alignment and abstains from any training, gradient computation, or parameter updates. Experimental results evaluated by GPT-4 and humans demonstrate the effectiveness of RAIN: on the HH dataset, RAIN improves the harmlessness rate of LLaMA 30B from 82% of vanilla inference to 97%, while maintaining the helpfulness rate. On the TruthfulQA dataset, RAIN improves the truthfulness of the already-well-aligned LLaMA-2-chat 13B model by 5%.

Zian Jia, Yun Xiong, Yuhong Nan et al.

Advance Persistent Threats (APTs), adopted by most delicate attackers, are becoming increasing common and pose great threat to various enterprises and institutions. Data provenance analysis on provenance graphs has emerged as a common approach in APT detection. However, previous works have exhibited several shortcomings: (1) requiring attack-containing data and a priori knowledge of APTs, (2) failing in extracting the rich contextual information buried within provenance graphs and (3) becoming impracticable due to their prohibitive computation overhead and memory consumption. In this paper, we introduce MAGIC, a novel and flexible self-supervised APT detection approach capable of performing multi-granularity detection under different level of supervision. MAGIC leverages masked graph representation learning to model benign system entities and behaviors, performing efficient deep feature extraction and structure abstraction on provenance graphs. By ferreting out anomalous system behaviors via outlier detection methods, MAGIC is able to perform both system entity level and batched log level APT detection. MAGIC is specially designed to handle concept drift with a model adaption mechanism and successfully applies to universal conditions and detection scenarios. We evaluate MAGIC on three widely-used datasets, including both real-world and simulated attacks. Evaluation results indicate that MAGIC achieves promising detection results in all scenarios and shows enormous advantage over state-of-the-art APT detection approaches in performance overhead.

Xiaobin Fan, Xiaoping Wang, Kai Lu et al.

Nearest neighbor search supports important applications in many domains, such as database, machine learning, computer vision. Since the computational cost for accurate search is too high, the community turned to the research of approximate nearest neighbor search (ANNS). Among them, graph-based algorithm is one of the most important branches. Research by Fu et al. shows that the algorithms based on Monotonic Search Network (MSNET), such as NSG and NSSG, have achieved the state-of-the-art search performance in efficiency. The MSNET is dedicated to achieving monotonic search with minimal out-degree of nodes to pursue high efficiency. However, the current MSNET designs did not optimize the probability of the monotonic search, and the lower bound of the probability is only 50%. If they fail in monotonic search stage, they have to suffer tremendous backtracking cost to achieve the required accuracy. This will cause performance problems in search efficiency. To address this problem, we propose (r,p)-MSNET, which achieves guaranteed probability on monotonic search. Due to the high building complexity of a strict (r,p)-MSNET, we propose TBSG, which is an approximation with low complexity. Experiment conducted on four million-scaled datasets show that TBSG outperforms existing state-of-the-art graph-based algorithms in search efficiency. Our code has been released on Github.