Qisheng Zhang

Zhen Guo, Zelin Wan, Qisheng Zhang et al.

An in-depth understanding of uncertainty is the first step to making effective decisions under uncertainty. Deep/machine learning (ML/DL) has been hugely leveraged to solve complex problems involved with processing high-dimensional data. However, reasoning and quantifying different types of uncertainties to achieve effective decision-making have been much less explored in ML/DL than in other Artificial Intelligence (AI) domains. In particular, belief/evidence theories have been studied in KRR since the 1960s to reason and measure uncertainties to enhance decision-making effectiveness. We found that only a few studies have leveraged the mature uncertainty research in belief/evidence theories in ML/DL to tackle complex problems under different types of uncertainty. In this survey paper, we discuss several popular belief theories and their core ideas dealing with uncertainty causes and types and quantifying them, along with the discussions of their applicability in ML/DL. In addition, we discuss three main approaches that leverage belief theories in Deep Neural Networks (DNNs), including Evidential DNNs, Fuzzy DNNs, and Rough DNNs, in terms of their uncertainty causes, types, and quantification methods along with their applicability in diverse problem domains. Based on our in-depth survey, we discuss insights, lessons learned, limitations of the current state-of-the-art bridging belief theories and ML/DL, and finally, future research directions.

Zhen Guo, Qi Zhang, Xinwei An et al.

Due to various and serious adverse impacts of spreading fake news, it is often known that only people with malicious intent would propagate fake news. However, it is not necessarily true based on social science studies. Distinguishing the types of fake news spreaders based on their intent is critical because it will effectively guide how to intervene to mitigate the spread of fake news with different approaches. To this end, we propose an intent classification framework that can best identify the correct intent of fake news. We will leverage deep reinforcement learning (DRL) that can optimize the structural representation of each tweet by removing noisy words from the input sequence when appending an actor to the long short-term memory (LSTM) intent classifier. Policy gradient DRL model (e.g., REINFORCE) can lead the actor to a higher delayed reward. We also devise a new uncertainty-aware immediate reward using a subjective opinion that can explicitly deal with multidimensional uncertainty for effective decision-making. Via 600K training episodes from a fake news tweets dataset with an annotated intent class, we evaluate the performance of uncertainty-aware reward in DRL. Evaluation results demonstrate that our proposed framework efficiently reduces the number of selected words to maintain a high 95\% multi-class accuracy.

Qisheng Zhang, Zhen Guo, Audun Jøsang et al.

Proximal Policy Optimization (PPO) is a highly popular policy-based deep reinforcement learning (DRL) approach. However, we observe that the homogeneous exploration process in PPO could cause an unexpected stability issue in the training phase. To address this issue, we propose PPO-UE, a PPO variant equipped with self-adaptive uncertainty-aware explorations (UEs) based on a ratio uncertainty level. The proposed PPO-UE is designed to improve convergence speed and performance with an optimized ratio uncertainty level. Through extensive sensitivity analysis by varying the ratio uncertainty level, our proposed PPO-UE considerably outperforms the baseline PPO in Roboschool continuous control tasks.

Ruwei Pan, Jiangshuai Wang, Qisheng Zhang et al.

Large language models (LLMs) have achieved substantial progress in repository-level code generation. However, solving the same repository-level task often requires multiple attempts, while existing methods still optimize each attempt in isolation and do not preserve or reuse task-specific state across attempts. In this paper, we propose LiveCoder, a novel framework for repository-level code generation based on cross-attempt knowledge optimization. LiveCoder maintains persistent task-specific state from prior attempts to guide subsequent generation. This state includes success knowledge, which captures reusable signals from previously strong repositories, failure knowledge, which records unsuccessful outcomes and their diagnostic signals, and a historical-best repository, which preserves the strongest result found so far and prevents regression. These components collectively transform repeated repository generation into a persistent, knowledge-driven optimization process. We evaluate LiveCoder using four frontier LLMs on two representative repository-level code generation benchmarks. Extensive experimental results demonstrate the effectiveness and efficiency of LiveCoder, improving the functional score by up to 22.94 percentage points, increasing repository reuse to 81.58%, and reducing cost by up to 53.63% on RAL-Bench while maintaining broadly stable non-functional quality.

Haonan Li, Tianjun Sun, Yongqing Wang et al.

Multi-server MCP agents create an information-flow control problem: faithful tool composition can turn individually benign read/write permissions into cross-boundary credential propagation -- a structural side effect of workflow topology, not necessarily malicious model behavior. We present MCPHunt, to our knowledge the first controlled benchmark that isolates non-adversarial, verbatim credential propagation across multi-server MCP trust boundaries, with three methodological contributions: (1) canary-based taint tracking that reduces propagation detection to objective string matching; (2) an environment-controlled coverage design with risky, benign, and hard-negative conditions that validates pipeline soundness and controls for credential-format confounds; (3) CRS stratification that disentangles task-mandated propagation (faithful execution of verbatim-transfer instructions) from policy-violating propagation (credentials included despite the option to redact). Across 3,615 main-benchmark traces from 5 models spanning 147 tasks and 9 mechanism families, policy-violating propagation rates reach 11.5--41.3% across all models. This propagation is pathway-specific (25x cross-mechanism range) and concentrated in browser-mediated data flows; hard-negative controls provide evidence that production-format credentials are not necessary -- prompt-directed cross-boundary data flow is sufficient. A prompt-mitigation study across 3 models reduces policy-violating propagation by up to 97% while preserving 80.5% utility, but effectiveness varies with instruction-following capability -- suggesting that prompt-level defenses alone may not suffice. Code, traces, and labeling pipeline are released under MIT and CC BY 4.0.

Qisheng Zhang, Abdullah Zubair Mohammed, Zelin Wan et al.

Diversity-based security approaches have been studied for several decades since the 1970's. The concept of diversity-by-design emerged in the 1980's and, since then, diversity-based system design research has been explored to build more secure and dependable systems. In this work, we are particularly interested in providing an in-depth, comprehensive survey of existing diversity-based approaches, insights, and future work directions for those who want to conduct research on developing secure and dependable cyber-physical systems (CPSs) using diversity as a system design feature. To be specific, this survey paper provides: (i) The common concept of diversity based on a multidisciplinary study of diversity from nine different fields along with the historical evolution of diversity-by-design for security; (ii) The design principles of diversity-based approaches; (iii) The key benefits and caveats of using diversity-by-design; (iv) The key concerns of CPS environments in introducing diversity-by-design; (v) A variety of existing diversity-based approaches based on five different classifications; (vi) The types of attacks mitigated by existing diversity-based approaches; (vii) The overall trends of evaluation methodologies used in diversity-based approaches, in terms of metrics, datasets, and testbeds; and (viii) The insights, lessons, and gaps identified from this extensive survey.

Qisheng Zhang, Jin-Hee Cho, Terrence J. Moore et al.

By leveraging the principle of software polyculture to ensure security in a network, we proposed a vulnerability-based software diversity metric to determine how a network topology can be adapted to minimize security vulnerability while maintaining maximum network connectivity. Our proposed software diversity-based adaptation (SDA) scheme estimates a node's software diversity based on the vulnerabilities of software packages installed on other nodes on attack paths reachable to the node and employs it for edge adaptations, such as removing an edge with a neighboring node that exposes high security vulnerability because two connected nodes use the same software packages or a neighboring node may have high software vulnerability or adding an edge with another node with less or no security vulnerability because the two nodes use different software packages or have low vulnerabilities associated with them. To validate the proposed SDA scheme, we conducted extensive experiments comparing the proposed SDA scheme with counterpart baseline schemes in real networks. Our simulation experimental results proved the outperformance of our proposed SDA compared to the existing counterparts and provided insightful findings in terms of the effectiveness and efficiency of the proposed SDA scheme under three real network topologies with vastly different network density.