Li Li

Zhihao Lin, Wei Ma, Mingyi Zhou et al.

In recent years, Large Language Models (LLMs) have gained widespread use, raising concerns about their security. Traditional jailbreak attacks, which often rely on the model internal information or have limitations when exploring the unsafe behavior of the victim model, limiting their reducing their general applicability. In this paper, we introduce PathSeeker, a novel black-box jailbreak method, which is inspired by the game of rats escaping a maze. We think that each LLM has its unique "security maze", and attackers attempt to find the exit learning from the received feedback and their accumulated experience to compromise the target LLM's security defences. Our approach leverages multi-agent reinforcement learning, where smaller models collaborate to guide the main LLM in performing mutation operations to achieve the attack objectives. By progressively modifying inputs based on the model's feedback, our system induces richer, harmful responses. During our manual attempts to perform jailbreak attacks, we found that the vocabulary of the response of the target model gradually became richer and eventually produced harmful responses. Based on the observation, we also introduce a reward mechanism that exploits the expansion of vocabulary richness in LLM responses to weaken security constraints. Our method outperforms five state-of-the-art attack techniques when tested across 13 commercial and open-source LLMs, achieving high attack success rates, especially in strongly aligned commercial models like GPT-4o-mini, Claude-3.5, and GLM-4-air with strong safety alignment. This study aims to improve the understanding of LLM security vulnerabilities and we hope that this sturdy can contribute to the development of more robust defenses.

Li Li, Jean-Pierre S. El Rami, Adrian Taylor et al.

This work aims to enable autonomous agents for network cyber operations (CyOps) by applying reinforcement and deep reinforcement learning (RL/DRL). The required RL training environment is particularly challenging, as it must balance the need for high-fidelity, best achieved through real network emulation, with the need for running large numbers of training episodes, best achieved using simulation. A unified training environment, namely the Cyber Gym for Intelligent Learning (CyGIL) is developed where an emulated CyGIL-E automatically generates a simulated CyGIL-S. From preliminary experimental results, CyGIL-S is capable to train agents in minutes compared with the days required in CyGIL-E. The agents trained in CyGIL-S are transferrable directly to CyGIL-E showing full decision proficiency in the emulated "real" network. Enabling offline RL, the CyGIL solution presents a promising direction towards sim-to-real for leveraging RL agents in real-world cyber networks.

Li Li, Jean-Pierre S. El Rami, Adrian Taylor et al.

Autonomous cyber agents may be developed by applying reinforcement and deep reinforcement learning (RL/DRL), where agents are trained in a representative environment. The training environment must simulate with high-fidelity the network Cyber Operations (CyOp) that the agent aims to explore. Given the complexity of net-work CyOps, a good simulator is difficult to achieve. This work presents a systematic solution to automatically generate a high-fidelity simulator in the Cyber Gym for Intelligent Learning (CyGIL). Through representation learning and continuous learning, CyGIL provides a unified CyOp training environment where an emulated CyGIL-E automatically generates a simulated CyGIL-S. The simulator generation is integrated with the agent training process to further reduce the required agent training time. The agent trained in CyGIL-S is transferrable directly to CyGIL-E showing full transferability to the emulated "real" network. Experimental results are presented to demonstrate the CyGIL training performance. Enabling offline RL, the CyGIL solution presents a promising direction towards sim-to-real for leveraging RL agents in real-world cyber networks.

Yi Ju, Jiaman Wu, Zhihan Su et al.

Electric vehicle (EV) charging infrastructure is crucial for advancing EV adoption, managing charging loads, and ensuring equitable transportation electrification. However, there remains a notable gap in comprehensive accessibility metrics that integrate the mobility of the users. This study introduces a novel accessibility metric, termed Trajectory-Integrated Public EVCS Accessibility (TI-acs), and uses it to assess public electric vehicle charging station (EVCS) accessibility for approximately 6 million residents in the San Francisco Bay Area based on detailed individual trajectory data in one week. Unlike conventional home-based metrics, TI-acs incorporates the accessibility of EVCS along individuals' travel trajectories, bringing insights on more public charging contexts, including public charging near workplaces and charging during grid off-peak periods. As of June 2024, given the current public EVCS network, Bay Area residents have, on average, 7.5 hours and 5.2 hours of access per day during which their stay locations are within 1 km (i.e. 10-12 min walking) of a public L2 and DCFC charging port, respectively. Over the past decade, TI-acs has steadily increased from the rapid expansion of the EV market and charging infrastructure. However, spatial disparities remain significant, as reflected in Gini indices of 0.38 (L2) and 0.44 (DCFC) across census tracts. Additionally, our analysis reveals racial disparities in TI-acs, driven not only by variations in charging infrastructure near residential areas but also by differences in their mobility patterns.

Qi Sun, Hang Zhou, Wengang Zhou et al.

Synthesizing realistic 3D indoor scenes is a challenging task that traditionally relies on manual arrangement and annotation by expert designers. Recent advances in autoregressive models have automated this process, but they often lack semantic understanding of the relationships and hierarchies present in real-world scenes, yielding limited performance. In this paper, we propose Forest2Seq, a framework that formulates indoor scene synthesis as an order-aware sequential learning problem. Forest2Seq organizes the inherently unordered collection of scene objects into structured, ordered hierarchical scene trees and forests. By employing a clustering-based algorithm and a breadth-first traversal, Forest2Seq derives meaningful orderings and utilizes a transformer to generate realistic 3D scenes autoregressively. Experimental results on standard benchmarks demonstrate Forest2Seq's superiority in synthesizing more realistic scenes compared to top-performing baselines, with significant improvements in FID and KL scores. Our additional experiments for downstream tasks and ablation studies also confirm the importance of incorporating order as a prior in 3D scene generation.

Linxin Song, Yutong Dai, Viraj Prabhu et al.

Autonomous agents that operate computers via Graphical User Interfaces (GUIs) often struggle with efficiency and reliability on complex, long-horizon tasks. While augmenting these agents with planners can improve task decomposition, they remain constrained by the inherent limitations of performing all actions through GUI manipulation, leading to brittleness and inefficiency. In this work, we introduce a more robust and flexible paradigm: enabling agents to use coding as a enhanced action. We present CoAct-1, a novel multi-agent system that synergistically combines GUI-based control with direct programmatic execution. CoAct-1 features an Orchestrator that dynamically delegates subtasks to either a conventional GUI Operator or a specialized Programmer agent, which can write and execute Python or Bash scripts. This hybrid approach allows the agent to bypass inefficient GUI action sequences for tasks like file management and data processing, while still leveraging visual interaction when necessary. We evaluate our system on the challenging OSWorld benchmark, where CoAct-1 achieves a new state-of-the-art success rate of 60.76%, significantly outperforming prior methods. Furthermore, our approach dramatically improves efficiency, reducing the average number of steps required to complete a task to just 10.15, compared to 15 for leading GUI agents. Our results demonstrate that integrating coding as a core action provides a more powerful, efficient, and scalable path toward generalized computer automation.

Jianfeng Cai, Jinhua Zhu, Ruopei Sun et al.

Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs) by modeling human preferences with a learnable reward model and employing a reinforcement learning algorithm to maximize the reward model's scores. However, these reward models are susceptible to exploitation through various superficial confounding factors, with length bias emerging as a particularly significant concern. Moreover, while the pronounced impact of length bias on preference modeling suggests that LLMs possess an inherent sensitivity to length perception, our preliminary investigations reveal that fine-tuned LLMs consistently struggle to adhere to explicit length instructions. To address these two limitations, we propose a novel framework wherein the reward model explicitly differentiates between human semantic preferences and response length requirements. Specifically, we introduce a $\textbf{R}$esponse-$\textbf{c}$onditioned $\textbf{B}$radley-$\textbf{T}$erry (Rc-BT) model that enhances the model's capability in length bias mitigating and length instruction following, through training on our augmented dataset. Furthermore, we propose the Rc-RM and Rc-DPO algorithm to leverage the Rc-BT model for reward modeling and direct policy optimization (DPO) of LLMs, simultaneously mitigating length bias and promoting adherence to length instructions. Extensive experiments across various foundational models and datasets demonstrate the effectiveness and generalizability of our approach.

Faizan Contractor, Li Li, Ranwa Al Mallah

Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained policies. However, by sharing information such as known or suspected ongoing threats, effective communication can lead to improved decision-making in the cyber battle space. We propose a game design where defender agents learn to communicate and defend against imminent cyber threats by playing training games in the Cyber Operations Research Gym, using the Differentiable Inter Agent Learning algorithm adapted to the cyber operational environment. The tactical policies learned by these autonomous agents are akin to those of human experts during incident responses to avert cyber threats. In addition, the agents simultaneously learn minimal cost communication messages while learning their defence tactical policies.

Junqi Liao, Yao Li, Zhuoyuan Li et al.

To address the real-time analysis requirements of video streaming applications, we propose an innovative inter-relation-aware video complexity analyzer (IVCA) to enhance the existing video complexity analyzer (VCA). The IVCA overcomes the limitations of the VCA by incorporating inter-frame relations, focusing on inter motion and reference structure. To begin with, we improve the accuracy of temporal features by integrating feature-domain motion estimation into the IVCA framework, which allows for a more nuanced understanding of motion across frames. Furthermore, inspired by the hierarchical reference structures utilized in modern codecs, we introduce layer-aware weights that effectively adjust the contributions of frame complexity across different layers, ensuring a more balanced representation of video characteristics. In addition, we broaden the analysis of temporal features by considering reference frames rather than relying solely on the preceding frame, thereby enriching the contextual understanding of video content. Experimental results demonstrate a significant enhancement in complexity estimation accuracy achieved by the IVCA, coupled with a negligible increase in time complexity, indicating its potential for real-time applications in video streaming scenarios. This advancement not only improves video processing efficiency but also paves the way for more sophisticated analytical tools in video technology.

Kahou Tam, Kewei Xu, Li Li et al.

Federated Learning (FL) has evolved as a powerful tool for collaborative model training across multiple entities, ensuring data privacy in sensitive sectors such as healthcare and finance. However, the introduction of the Right to Be Forgotten (RTBF) poses new challenges, necessitating federated unlearning to delete data without full model retraining. Traditional FL unlearning methods, not originally designed with domain specificity in mind, inadequately address the complexities of multi-domain scenarios, often affecting the accuracy of models in non-targeted domains or leading to uniform forgetting across all domains. Our work presents the first comprehensive empirical study on Federated Domain Unlearning, analyzing the characteristics and challenges of current techniques in multi-domain contexts. We uncover that these methods falter, particularly because they neglect the nuanced influences of domain-specific data, which can lead to significant performance degradation and inaccurate model behavior. Our findings reveal that unlearning disproportionately affects the model's deeper layers, erasing critical representational subspaces acquired during earlier training phases. In response, we propose novel evaluation methodologies tailored for Federated Domain Unlearning, aiming to accurately assess and verify domain-specific data erasure without compromising the model's overall integrity and performance. This investigation not only highlights the urgent need for domain-centric unlearning strategies in FL but also sets a new precedent for evaluating and implementing these techniques effectively.

Jeremy Every, Li Li, Youguang G. Guo et al.

Determining the optimal size and orientation of small-scale residential based PV arrays will become increasingly complex in the future smart grid environment with the introduction of smart meters and dynamic tariffs. However consumers can leverage the availability of smart meter data to conduct a more detailed exploration of PV investment options for their particular circumstances. In this paper, an optimization method for PV orientation and sizing is proposed whereby maximizing the PV investment value is set as the defining objective. Solar insolation and PV array models are described to form the basis of the PV array optimization strategy. A constrained particle swarm optimization algorithm is selected due to its strong performance in non-linear applications. The optimization algorithm is applied to real-world metered data to quantify the possible investment value of a PV installation under different energy retailers and tariff structures. The arrangement with the highest value is determined to enable prospective small-scale PV investors to select the most cost-effective system.