Gradient Co-occurrence Analysis for Detecting Unsafe Prompts in Large Language Models

Unsafe prompts pose significant safety risks to large language models (LLMs). Existing methods for detecting unsafe prompts rely on data-driven fine-tuning to train guardrail models, necessitating significant data and computational resources. In contrast, recent few-shot gradient-based methods emerge, requiring only few safe and unsafe reference prompts. A gradient-based approach identifies unsafe prompts by analyzing consistent patterns of the gradients of safety-critical parameters in LLMs. Although effective, its restriction to directional similarity (cosine similarity) introduces ``directional bias'', limiting its capability to identify unsafe prompts. To overcome this limitation, we introduce GradCoo, a novel gradient co-occurrence analysis method that expands the scope of safety-critical parameter identification to include unsigned gradient similarity, thereby reducing the impact of ``directional bias'' and enhancing the accuracy of unsafe prompt detection. Comprehensive experiments on the widely-used benchmark datasets ToxicChat and XStest demonstrate that our proposed method can achieve state-of-the-art (SOTA) performance compared to existing methods. Moreover, we confirm the generalizability of GradCoo in detecting unsafe prompts across a range of LLM base models with various sizes and origins.

Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach

A Large Language Model (LLM) tends to generate inconsistent and sometimes contradictory outputs when presented with a prompt that has equivalent semantics but is expressed differently from the original prompt. To achieve semantic consistency of an LLM, one of the key approaches is to finetune the model with prompt-output pairs with semantically equivalent meanings. Despite its effectiveness, a data-driven finetuning method incurs substantial computation costs in data preparation and model optimization. In this regime, an LLM is treated as a ``black box'', restricting our ability to gain deeper insights into its internal mechanism. In this paper, we are motivated to enhance the semantic consistency of LLMs through a more interpretable method (i.e., model editing) to this end. We first identify the model components (i.e., attention heads) that have a key impact on the semantic consistency of an LLM. We subsequently inject biases into the output of these model components along the semantic-consistency activation direction. It is noteworthy that these modifications are cost-effective, without reliance on mass manipulations of the original model parameters. Through comprehensive experiments on the constructed NLU and open-source NLG datasets, our method demonstrates significant improvements in the semantic consistency and task performance of LLMs. Additionally, our method exhibits promising generalization capabilities by performing well on tasks beyond the primary tasks.

LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models

Large Language Models (LLMs) often generate inconsistent responses when prompted with semantically equivalent paraphrased inputs. Recently, activation steering, a technique that modulates LLM behavior by adjusting their latent representations during inference time, has been explored to improve the semantic consistency of LLMs. However, these methods typically operate at the model component level, such as layer hidden states or attention heads. They face a challenge due to the ``polysemanticity issue'', where the model components of LLMs typically encode multiple entangled features, making precise steering difficult. To address this challenge, we drill down to feature-level representations and propose LF-Steering, a novel activation steering approach to precisely identify latent feature representations responsible for semantic inconsistency. More specifically, our method maps the hidden states of relevant transformer layer into a sparsely activated, high-dimensional feature space based on a sparse autoencoder (SAE), ensuring model steering based on decoupled feature representations with minimal interference. Comprehensive experiments on both NLU and NLG datasets demonstrate the effectiveness of our method in enhancing semantic consistency, resulting in significant performance gains for various NLU and NLG tasks.

Multipath Component-Aided Signal Processing for Integrated Sensing and Communication Systems

Integrated sensing and communication (ISAC) has emerged as a pivotal enabling technology for sixth-generation (6G) mobile communication system. The ISAC research in dense urban areas has been plaguing by severe multipath interference, propelling the thorough research of ISAC multipath interference elimination. However, transforming the multipath component (MPC) from enemy into friend is a viable and mutually beneficial option. In this paper, we preliminarily explore the MPC-aided ISAC signal processing and apply a space-time code to improve the ISAC performance. Specifically, we propose a symbol-level fusion for MPC-aided localization (SFMC) scheme to achieve robust and high-accuracy localization, and apply a Khatri-Rao space-time (KRST) code to improve the communication and sensing performance in rich multipath environment. Simulation results demonstrate that the proposed SFMC scheme has more robust localization performance with higher accuracy, compared with the existing state-of-the-art schemes. The proposed SFMC would benefit highly reliable communication and sub-meter level localization in rich multipath scenarios.

Contrastive Representation for Interactive Recommendation

Interactive Recommendation (IR) has gained significant attention recently for its capability to quickly capture dynamic interest and optimize both short and long term objectives. IR agents are typically implemented through Deep Reinforcement Learning (DRL), because DRL is inherently compatible with the dynamic nature of IR. However, DRL is currently not perfect for IR. Due to the large action space and sample inefficiency problem, training DRL recommender agents is challenging. The key point is that useful features cannot be extracted as high-quality representations for the recommender agent to optimize its policy. To tackle this problem, we propose Contrastive Representation for Interactive Recommendation (CRIR). CRIR efficiently extracts latent, high-level preference ranking features from explicit interaction, and leverages the features to enhance users' representation. Specifically, the CRIR provides representation through one representation network, and refines it through our proposed Preference Ranking Contrastive Learning (PRCL). The key insight of PRCL is that it can perform contrastive learning without relying on computations involving high-level representations or large potential action sets. Furthermore, we also propose a data exploiting mechanism and an agent training mechanism to better adapt CRIR to the DRL backbone. Extensive experiments have been carried out to show our method's superior improvement on the sample efficiency while training an DRL-based IR agent.

Distributed Cooperative Positioning in Dense Wireless Networks: A Neural Network Enhanced Fast Convergent Parametric Message Passing Method

Parametric message passing (MP) is a promising technique that provides reliable marginal probability distributions for distributed cooperative positioning (DCP) based on factor graphs (FG), while maintaining minimal computational complexity. However, conventional parametric MP-based DCP methods may fail to converge in dense wireless networks due to numerous short loops on FG. Additionally, the use of inappropriate message approximation techniques can lead to increased sensitivity to initial values and significantly slower convergence rates. To address the challenging DCP problem modeled by a loopy FG, we propose an effective graph neural network enhanced fast convergent parametric MP (GNN--FCPMP) method. We first employ Chebyshev polynomials to approximate the nonlinear terms present in the FG-based spatio-temporal messages. This technique facilitates the derivation of globally precise, closed-form representations for each message transmitted across the FG. Then, the parametric representations of spatial messages are meticulously refined through data-driven graph neural networks (GNNs). Conclusively, by performing inference on the FG, we derive more accurate closed-form expressions for the a posteriori distributions of node positions. Numerical results substantiate the capability of GNN--FCPMP to significantly enhance positioning accuracy within wireless networks characterized by high-density loops and ensure rapid convergence.

Overview of AI and Communication for 6G Network: Fundamentals, Challenges, and Future Research Opportunities

With the increasing demand for seamless connectivity and intelligent communication, the integration of artificial intelligence (AI) and communication for sixth-generation (6G) network is emerging as a revolutionary architecture. This paper presents a comprehensive overview of AI and communication for 6G networks, emphasizing their foundational principles, inherent challenges, and future research opportunities. We commence with a retrospective analysis of AI and the evolution of large-scale AI models, underscoring their pivotal roles in shaping contemporary communication technologies. The discourse then transitions to a detailed exposition of the envisioned integration of AI within 6G networks, delineated across three progressive developmental stages. The initial stage, AI for Network, focuses on employing AI to augment network performance, optimize efficiency, and enhance user service experiences. The subsequent stage, Network for AI, highlights the role of the network in facilitating and buttressing AI operations and presents key enabling technologies, including digital twins for AI and semantic communication. In the final stage, AI as a Service, it is anticipated that future 6G networks will innately provide AI functions as services and support application scenarios like immersive communication and intelligent industrial robots. Specifically, we have defined the quality of AI service, which refers to the measurement framework system of AI services within the network. In addition to these developmental stages, we thoroughly examine the standardization processes pertinent to AI in network contexts, highlighting key milestones and ongoing efforts. Finally, we outline promising future research opportunities that could drive the evolution and refinement of AI and communication for 6G, positioning them as a cornerstone of next-generation communication infrastructure.

Static-Dynamic Class-level Perception Consistency in Video Semantic Segmentation

Video semantic segmentation(VSS) has been widely employed in lots of fields, such as simultaneous localization and mapping, autonomous driving and surveillance. Its core challenge is how to leverage temporal information to achieve better segmentation. Previous efforts have primarily focused on pixel-level static-dynamic contexts matching, utilizing techniques such as optical flow and attention mechanisms. Instead, this paper rethinks static-dynamic contexts at the class level and proposes a novel static-dynamic class-level perceptual consistency (SD-CPC) framework. In this framework, we propose multivariate class prototype with contrastive learning and a static-dynamic semantic alignment module. The former provides class-level constraints for the model, obtaining personalized inter-class features and diversified intra-class features. The latter first establishes intra-frame spatial multi-scale and multi-level correlations to achieve static semantic alignment. Then, based on cross-frame static perceptual differences, it performs two-stage cross-frame selective aggregation to achieve dynamic semantic alignment. Meanwhile, we propose a window-based attention map calculation method that leverages the sparsity of attention points during cross-frame aggregation to reduce computation cost. Extensive experiments on VSPW and Cityscapes datasets show that the proposed approach outperforms state-of-the-art methods. Our implementation will be open-sourced on GitHub.

FairSort: Learning to Fair Rank for Personalized Recommendations in Two-Sided Platforms

Traditional recommendation systems focus on maximizing user satisfaction by suggesting their favorite items. This user-centric approach may lead to unfair exposure distribution among the providers. On the contrary, a provider-centric design might become unfair to the users. Therefore, this paper proposes a re-ranking model FairSort\footnote{\textbf{Reproducibility:}The code and datasets are available at \url{https://github.com/13543024276/FairSort}} to find a trade-off solution among user-side fairness, provider-side fairness, and personalized recommendations utility. Previous works habitually treat this issue as a knapsack problem, incorporating both-side fairness as constraints. In this paper, we adopt a novel perspective, treating each recommendation list as a runway rather than a knapsack. In this perspective, each item on the runway gains a velocity and runs within a specific time, achieving re-ranking for both-side fairness. Meanwhile, we ensure the Minimum Utility Guarantee for personalized recommendations by designing a Binary Search approach. This can provide more reliable recommendations compared to the conventional greedy strategy based on the knapsack problem. We further broaden the applicability of FairSort, designing two versions for online and offline recommendation scenarios. Theoretical analysis and extensive experiments on real-world datasets indicate that FairSort can ensure more reliable personalized recommendations while considering fairness for both the provider and user.

UAV's Rotor Micro-Doppler Feature Extraction Using Integrated Sensing and Communication Signal: Algorithm Design and Testbed Evaluation

With the rapid application of unmanned aerial vehicles (UAVs) in urban areas, the identification and tracking of hovering UAVs have become critical challenges, significantly impacting the safety of aircraft take-off and landing operations. As a promising technology for 6G mobile systems, integrated sensing and communication (ISAC) can be used to detect high-mobility UAVs with a low deployment cost. The micro-Doppler signals from UAV rotors can be leveraged to address the detection of low-mobility and hovering UAVs using ISAC signals. However, determining whether the frame structure of the ISAC system can be used to identify UAVs, and how to accurately capture the weak rotor micro-Doppler signals of UAVs in complex environments, remain two challenging problems. This paper first proposes a novel frame structure for UAV micro-Doppler extraction and the representation of UAV micro-Doppler signals within the channel state information (CSI). Furthermore, to address complex environments and the interference caused by UAV body vibrations, the rotor micro-Doppler null space pursuit (rmD-NSP) algorithm and the feature extraction algorithm synchroextracting transform (SET) are designed to effectively separate UAV's rotor micro-Doppler signals and enhance their features in the spectrogram. Finally, both simulation and hardware testbed demonstrate that the proposed rmD-NSP algorithm enables the ISAC base station (BS) to accurately and completely extract UAV's rotor micro-Doppler signals. Within a 0.1s observation period, ISAC BS successfully captures eight rotations of the DJI M300 RTK UAV's rotor in urban environments. Compared to the existing AM-FM NSP and NSP signal decomposition algorithms, the integrity of the rotor micro-Doppler features is improved by 60%.