Jian Gao

EAAI Journal 2026 Journal Article

Sample augmentation-based adversarial training method to counter evasive spectre attacks

• Zhongkai Tong
• Jian Gao
• Deyu Yuan
• Gang Liu

Microarchitectural attacks exploit subtle processor-level vulnerabilities to extract sensitive data, posing persistent challenges to modern hardware security. Although artificial intelligence (AI)–assisted detection using hardware performance counters (HPCs) provides a low-overhead defense, its reliability remains limited when facing evasive variants that deliberately mask their microarchitectural footprints. In this work, we present Evasive Spectre. This novel Spectre variant incorporates controlled delay operations to bypass state-of-the-art HPC-based AI detectors, thereby exposing inherent weaknesses in existing detection systems. To mitigate these limitations, we propose a sample-augmentation-based adversarial training framework that improves model robustness by periodically injecting adversarial samples and leveraging combined HPC feature representations. Experiments on Intel Corporation (Intel) i7-7700 and Advanced Micro Devices (AMD) Ryzen 7-4800H platforms demonstrate over 99% detection accuracy against both Spectre and the proposed Evasive Spectre, with a maximum runtime overhead of only 1. 7%. These results underscore a lightweight, scalable, and robust defense paradigm that advances the application of adversarial learning to intelligent hardware security in the AI-driven era.

ICML Conference 2025 Conference Paper

AnalogGenie-Lite: Enhancing Scalability and Precision in Circuit Topology Discovery through Lightweight Graph Modeling

• Jian Gao
• Weidong Cao 0001
• Xuan Zhang 0001

The sustainable performance improvements of integrated circuits (ICs) drive the continuous advancement of nearly all transformative technologies. Since its invention, IC performance enhancements have been dominated by scaling the semiconductor technology. Yet, as Moore’s law tapers off, a crucial question arises: How can we sustain IC performance in the post-Moore era? Creating new circuit topologies has emerged as a promising pathway to address this fundamental need. This work proposes AnalogGenie-Lite, a decoder-only transformer that discovers novel analog IC topologies with significantly enhanced scalability and precision via lightweight graph modeling. AnalogGenie-Lite makes several unique contributions, including concise device-pin representations (i. e. , advancing the best prior art from $O\left(n^2\right)$ to $O\left(n\right)$), frequent sub-graph mining, and optimal sequence modeling. Compared to state-of-the-art circuit topology discovery methods, it achieves $5. 15\times$ to $71. 11\times$ gains in scalability and 23. 5% to 33. 6% improvements in validity. Case studies on other domains’ graphs are also provided to show the broader applicability of the proposed graph modeling approach. Source code: https: //github. com/xz-group/AnalogGenie-Lite.

ICLR Conference 2025 Conference Paper

AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologies

• Jian Gao
• Weidong Cao 0001
• Junyi Yang
• Xuan Zhang 0001

The massive and large-scale design of foundational semiconductor integrated circuits (ICs) is crucial to sustaining the advancement of many emerging and future technologies, such as generative AI, 5G/6G, and quantum computing. Excitingly, recent studies have shown the great capabilities of foundational models in expediting the design of digital ICs. Yet, applying generative AI techniques to accelerate the design of analog ICs remains a significant challenge due to critical domain-specific issues, such as the lack of a comprehensive dataset and effective representation methods for analog circuits. This paper proposes, $\textbf{AnalogGenie}$, a $\underline{\textbf{Gen}}$erat$\underline{\textbf{i}}$ve $\underline{\textbf{e}}$ngine for automatic design/discovery of $\underline{\textbf{Analog}}$ circuit topologies--the most challenging and creative task in the conventional manual design flow of analog ICs. AnalogGenie addresses two key gaps in the field: building a foundational comprehensive dataset of analog circuit topology and developing a scalable sequence-based graph representation universal to analog circuits. Experimental results show the remarkable generation performance of AnalogGenie in broadening the variety of analog ICs, increasing the number of devices within a single design, and discovering unseen circuit topologies far beyond any prior arts. Our work paves the way to transform the longstanding time-consuming manual design flow of analog ICs to an automatic and massive manner powered by generative AI. Our source code is available at https://github.com/xz-group/AnalogGenie.

AAAI Conference 2025 Conference Paper

Enhancing Elusive Clues in Knowledge Learning by Contrasting Attention of Language Models

• Jian Gao
• Xiao Zhang
• Miao Li
• Ji Wu

Causal language models acquire vast amount of knowledge from general text corpus during pretraining, but the efficiency of knowledge learning is known to be unsatisfactory, especially when learning from knowledge-dense and small-sized corpora. The deficiency can come from long-distance dependencies which are hard to capture by language models, and overfitting to co-occurrence patterns and distracting clues in the training text. To address these issues, the paper proposes a method to enhance knowledge learning during language model pretraining, by enhancing elusive but important clues in text discovered by the language model themselves. We found that larger language models pay more attention to non-obvious but important clues, which are often overlooked by smaller language models. Therefore, we can identify these clues by contrasting the attention weights of large and small language models. We use the identified clues as a guide to perform token-dropout data augmentation on the training text, and observed a significant boost in both small and large models' performance in fact memorization. This shows that the behavior contrast between more and less-performant language models contains important clues for knowledge learning, and it can be "amplified" for a straight-forward improvement in knowledge learning efficiency.

IJCAI Conference 2025 Conference Paper

InfVC: An Inference-Enhanced Local Search Algorithm for the Minimum Vertex Cover Problem in Massive Graphs

• Rui Sun
• Peiyan Liu
• Yiyuan Wang
• Zhaohui Liu
• Liping Du
• Jian Gao

The minimum vertex cover (MVC) problem is a classic NP-hard combinatorial optimization problem with extensive real-world applications. In this paper, we propose an efficient local search algorithm, InfVC, to solve the MVC in massive graphs, which comprises three ideas. First, we introduce an inference-driven optimization strategy that explores better feasible solutions through inference rules. Second, we develop a structural-determined perturbation strategy that is motivated by the structure features of high-quality solutions, prioritizing high-degree vertices into the candidate solution to guide the search process to some potential high-quality search area. Third, we design a self-adaptive local search framework that dynamically balances exploration and exploitation through a perturbation management mechanism. Extensive experiments demonstrate that InfVC outperforms all the state-of-the-art algorithms on almost massive instances.

NeurIPS Conference 2024 Conference Paper

Pedestrian-Centric 3D Pre-collision Pose and Shape Estimation from Dashcam Perspective

• Meijun Wang
• Yu Meng
• Zhongwei Qiu
• Chao Zheng
• Yan Xu
• Xiaorui Peng
• Jian Gao

Pedestrian pre-collision pose is one of the key factors to determine the degree of pedestrian-vehicle injury in collision. Human pose estimation algorithm is an effective method to estimate pedestrian emergency pose from accident video. However, the pose estimation model trained by the existing daily human pose datasets has poor robustness under specific poses such as pedestrian pre-collision pose, and it is difficult to obtain human pose datasets in the wild scenes, especially lacking scarce data such as pedestrian pre-collision pose in traffic scenes. In this paper, we collect pedestrian-vehicle collision pose from the dashcam perspective of dashcam and construct the first Pedestrian-Vehicle Collision Pose dataset (PVCP) in a semi-automatic way, including 40k+ accident frames and 20K+ pedestrian pre-collision pose annotation (2D, 3D, Mesh). Further, we construct a Pedestrian Pre-collision Pose Estimation Network (PPSENet) to estimate the collision pose and shape sequence of pedestrians from pedestrian-vehicle accident videos. The PPSENet first estimates the 2D pose from the image (Image to Pose, ITP) and then lifts the 2D pose to 3D mesh (Pose to Mesh, PTM). Due to the small size of the dataset, we introduce a pre-training model that learns the human pose prior on a large number of pose datasets, and use iterative regression to estimate the pre-collision pose and shape of pedestrians. Further, we classify the pre-collision pose sequence and introduce pose class loss, which achieves the best accuracy compared with the existing relevant \textit{state-of-the-art} methods. Code and data are available for research at https: //github. com/wmj142326/PVCP.

AAAI Conference 2022 Conference Paper

An Exact Algorithm with New Upper Bounds for the Maximum k-Defective Clique Problem in Massive Sparse Graphs

• Jian Gao
• Zhenghang Xu
• Ruizhi Li
• Minghao Yin

The Maximum k-Defective Clique Problem (MDCP), as a clique relaxation model, has been used to solve various problems. Because it is a hard computational task, previous works can hardly solve the MDCP for massive sparse graphs derived from real-world applications. In this work, we propose a novel branch-and-bound algorithm to solve the MDCP based on several new techniques. First, we propose two new upper bounds of the MDCP as well as corresponding reduction rules to remove redundant vertices and edges. The proposed reduction rules are particularly useful for massive graphs. Second, we present another new upper bound by counting missing edges between fixed vertices and an unfixed vertex for cutting branches. We perform extensive computational experiments to evaluate our algorithm. Experimental results show that our reduction rules are very effective for removing redundant vertices and edges so that graphs are reduced greatly. Also, our algorithm can solve benchmark instances efficiently, and it has significantly better performance than state-of-the-art algorithms.

JAIR Journal 2022 Journal Article

Improving Simulated Annealing for Clique Partitioning Problems

• Jian Gao
• Yiqi Lv
• Minghao Liu
• Shaowei Cai
• Feifei Ma

The Clique Partitioning Problem (CPP) is essential in graph theory with a number of important applications. Due to its NP-hardness, efficient algorithms for solving this problem are very crucial for practical purposes, and simulated annealing is proved to be effective in state-of-the-art CPP algorithms. However, to make simulated annealing more efficient to solve large-scale CPPs, in this paper, we propose a new iterated simulated annealing algorithm. Several methods are proposed in our algorithm to improve simulated annealing. First, a new configuration checking strategy based on timestamp is presented and incorporated into simulated annealing to avoid search cycles. Afterwards, to enhance the local search ability of simulated annealing and speed up convergence, we combine our simulated annealing with a descent search method to solve the CPP. This method further improves solutions found by simulated annealing, and thus compensates for the local search effect. To further accelerate the convergence speed, we introduce a shrinking factor to decline initial temperature and then propose an iterated local search algorithm based on simulated annealing. Additionally, a restart strategy is adopted when the search procedure converges. Extensive experiments on benchmark instances of the CPP were carried out, and the results suggest that the proposed simulated annealing algorithm outperforms all the existing heuristic algorithms, including five state-of-the-art algorithms. Thus the best-known solutions for 34 instances out of 94 are updated. We also conduct comparative analyses of the proposed strategies and show their effectiveness.

YNICL Journal 2022 Journal Article

Rhythmic musical-electrical trigeminal nerve stimulation improves impaired consciousness

• Min Wu
• Benyan Luo
• Yamei Yu
• Xiaoxia Li
• Jian Gao
• Jingqi Li
• Bettina Sorger
• Lars Riecke

Accumulating evidence shows that consciousness is linked to neural oscillations in the thalamocortical system, suggesting that deficits in these oscillations may underlie disorders of consciousness (DOC). However, patient-friendly non-invasive treatments targeting this functional anomaly are still missing and the therapeutic value of oscillation restoration has remained unclear. We propose a novel approach that aims to restore DOC patients' thalamocortical oscillations by combining rhythmic trigeminal-nerve stimulation with comodulated musical stimulation ("musical-electrical TNS"). In a double-blind, placebo-controlled, parallel-group study, we recruited 63 patients with DOC and randomly assigned them to groups receiving gamma, beta, or sham musical-electrical TNS. The stimulation was applied for 40 min on five consecutive days. We measured patients' consciousness before and after the stimulation using behavioral indicators and neural responses to rhythmic auditory speech. We further assessed their outcomes one year later. We found that musical-electrical TNS reliably lead to improvements in consciousness and oscillatory brain activity at the stimulation frequency: 43.5 % of patients in the gamma group and 25 % of patients in the beta group showed an improvement of their diagnosis after being treated with the stimulation. This group of benefitting patients still showed more positive outcomes one year later. Moreover, patients with stronger behavioral benefits showed stronger improvements in oscillatory brain activity. These findings suggest that brain oscillations contribute to consciousness and that musical-electrical TNS may serve as a promising approach to improve consciousness and predict long-term outcomes in patients with DOC.

IJCAI Conference 2020 Conference Paper

Early and Efficient Identification of Useless Constraint Propagation for Alldifferent Constraints

• Xizhe Zhang
• Jian Gao
• Yizhi Lv
• Weixiong Zhang

Constraints propagation and backtracking are two basic techniques for solving constraint satisfaction problems (CSPs). During the search for a solution, the variable and value pairs that do not belong to any solution can be discarded by constraint propagation to ensure generalized arc consistency so as to avoid the fruitless search. However, constraint propagation is frequently invoked often with little effect on many CSPs. Much effort has been devoted to predicting when to invoke constraint propagation for solving a CSP; however, no effective approach has been developed for the alldifferent constraint. Here we present a novel theorem for identifying the edges in a value graph of alldifferent constraint whose removal can significantly reduce useless constraint propagation. We prove that if an alternating cycle exists for a prospectively removable edge that represents a variable-value assignment, the edge (and the assignment) can be discarded without constraint propagation. Based on this theorem, we developed a novel optimizing technique for early detection of useless constraint propagation which can be incorporated in any existing algorithm for alldifferent constraint. Our implementation of the new method achieved speedup by a factor of 1-5 over the state-of-art approaches on 93 benchmark problem instances in 8 domains. Furthermore, the new algorithm is scalable well and runs increasingly faster than the existing methods on larger problems.

YNICL Journal 2019 Journal Article

Structural connectome alterations in patients with disorders of consciousness revealed by 7-tesla magnetic resonance imaging

• Xufei Tan
• Zhen Zhou
• Jian Gao
• Fanxia Meng
• Yamei Yu
• Jie Zhang
• Fangping He
• Ruili Wei

Although the functional connectivity of patients with disorders of consciousness (DOC) has been widely examined, less is known about brain white matter connectivity. The aim of this study was to explore structural network alterations for the diagnosis and prognosis of patients with chronic DOC. Eleven DOC patients and 11 sex- and age-matched controls were included in the study. Participants underwent diffusion magnetic resonance imaging (MRI) and T1-weighted structural MRI at 7 tesla (7 T). Graph-theoretical analysis and network-based statistics were used to analyze the group differences. Two patients were scanned twice for a longitudinal study to examine the relationship between connectome metrics and the patients' prognoses. Compared with healthy controls, DOC patients showed significantly elevated transitivity (p < .001), local efficiency (p = .009), and clustering coefficient (p = .039). When comparing the connectome metrics within the three groups (healthy controls, minimally conscious state (MCS), and vegetative state/unresponsive wakefulness syndrome (VS/UWS)), significant group differences were observed in transitivity (p < .001) and local efficiency (p = .031). Significantly increased transitivity was observed in vegetative state/unresponsive wakefulness syndrome compared with minimally conscious state (p = .0217, Bonferroni corrected). Transitivity showed significant negative correlations with the Coma Recovery Scale-Revised score (r = -0.6902, p = .023), consistent with the longitudinal study results. A subnetwork with significantly decreased structural connections was identified using network-based statistical analysis comparing DOC patients with healthy controls, which was mainly located in the frontal cortex, limbic system, and occipital and parietal lobes. This preliminary study suggests that graph theoretical approaches for assessing white matter connectivity may enable various states of DOC to be distinguished. Of the metrics analyzed, transitivity had a critical role in distinguishing the diagnostic groups. Larger cohorts will be necessary to confirm the predictive value of 7 T MRI in the prognosis of DOC patients.

IJCAI Conference 2018 Conference Paper

An Exact Algorithm for Maximum k-Plexes in Massive Graphs

• Jian Gao
• Jiejiang Chen
• Minghao Yin
• Rong Chen
• Yiyuan Wang

The maximum k-plex, a generalization of maximum clique, is used to cope with a great number of real-world problems. The aim of this paper is to propose a novel exact k-plex algorithm that can deal with large-scaled graphs with millions of vertices and edges. Specifically, we first propose several new graph reduction methods through a careful analyzing of structures of induced subgraphs. Afterwards, we present a preprocessing method to simplify initial graphs. Additionally, we present a branch-and-bound algorithm integrating the reduction methods as well as a new dynamic vertex selection mechanism. We perform intensive experiments to evaluate our algorithm, and show that the proposed strategies are effective and our algorithm outperforms state-of-the-art algorithms, especially for real-world massive graphs.

IJCAI Conference 2018 Conference Paper

Finding Communities with Hierarchical Semantics by Distinguishing General and Specialized topics

• Ge Zhang
• Di Jin
• Jian Gao
• Pengfei Jiao
• Françoise Fogelman-Soulié
• Xin Huang

Using network topology and semantic contents to find topic-related communities is a new trend in the field of community detection. By analyzing texts in social networks, we find that topics in networked contents are often hierarchical. In most cases, they have a two-level semantic structure with general and specialized topics, to respectively denote common and specific interests of communities. However, the existing community detection methods ignore such a hierarchy and take all words used to describe node semantics from an identical perspective. This indiscriminate use of words leads to natural defects in depicting networked content in which the deep semantics is not fully utilized. To address this problem, we propose a novel probabilistic generative model. By distinguishing the general and specialized topics of words, our model not only can find community structures more accurately, but also provide two-level semantic interpretation for each community. We train the model by deriving an efficient inference method under the framework of variational expectation-maximization. We provide a case study to show the ability of our algorithm in deep semantic interpretability of communities. The superiority of our algorithm for community detection is further demonstrated in comparison with eight state-of-the-art algorithms on eight real-world networks.

AAAI Conference 2018 Short Paper

NuMWVC: A Novel Local Search for Minimum Weighted Vertex Cover Problem

• Ruizhi Li
• Shaowei Cai
• Shuli Hu
• Minghao Yin
• Jian Gao

The minimum weighted vertex cover (MWVC) problem is a well known combinatorial optimization problem with important applications. This paper introduces a novel local search algorithm called NuMWVC for MWVC based on three ideas. First, four reduction rules are introduced during the initial construction phase. Second, the configuration checking with aspiration is proposed to reduce cycling problem. Moreover, a self-adaptive vertex removing strategy is proposed to save time.

AAAI Conference 2011 Conference Paper

Hybrid Tractable Classes of Binary Quantified Constraint Satisfaction Problems

• Jian Gao
• Minghao Yin
• Junping Zhou