Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs.To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete and visually depictable, while safety concepts, like helpfulness, are abstract and lack visual referents.Inspired by the Self-Fulfilling mechanism underlying emergent misalignment, we propose Visual Self-Fulfilling Alignment (VSFA).VSFA fine-tunes vision-language models (VLMs) on neutral VQA tasks constructed around threat-related images, without any safety labels.Through repeated exposure to threat-related visual content, models internalize the implicit semantics of vigilance and caution, shaping safetyoriented personas.Experiments across multiple VLMs and safety benchmarks demonstrate that VSFA reduces the attack success rate, improves response quality, and mitigates over-refusal while preserving general capabilities.Our work extends the self-fulfilling mechanism from text to visual modalities, offering a label-free approach to VLMs alignment.

Wenrui Zhou, Mohamed Hendy, Shu Yang, Qingsong Yang, Zikun Guo, Yuyu Luo, Lijie Hu, Di Wang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Reliable behavior control is central to deploying Large Language Models (LLMs) on the web. Activation steering offers a tuning-free route to align attributes (e.g., truthfulness) that ensure trustworthy generation. Prevailing approaches rely on coarse heuristics and lack a principled account of where to steer and how strongly to intervene. To this end, we propose Position-wise Injection with eXact Estimated Levels (PIXEL), a position-wise activation steering framework that, in contrast to prior work, learns a property-aligned subspace from dual views (tail-averaged and end-token) and selects intervention strength via a constrained geometric objective with a closed-form solution, thereby adapting to token-level sensitivity without global hyperparameter tuning. PIXEL further performs sample-level orthogonal residual calibration to refine the global attribute direction and employs a lightweight position-scanning routine to identify receptive injection sites. We additionally provide representation-level guarantees for the minimal-intervention rule, supporting reliable alignment. Across diverse models and evaluation paradigms, PIXEL consistently improves attribute alignment while preserving model general capabilities, offering a practical and principled method for LLMs' controllable generation. Our code is available at https://anonymous.4open.science/r/PIXEL-Adaptive-Steering-95DC

Explainable AI (XAI) refers to techniques that provide human-understandable insights into the workings of AI models. Recently, the focus of XAI has been extended toward explaining Large Language Models (LLMs). This extension calls for a significant transformation in the XAI methodologies for two reasons. First, many existing XAI methods cannot be directly applied to LLMs due to their complexity and advanced capabilities. Second, as LLMs are increasingly deployed in diverse applications, the role of XAI shifts from merely opening the “black box” to actively enhancing the productivity and applicability of LLMs in real-world settings. Meanwhile, the conversation and generation abilities of LLMs can reciprocally enhance XAI. Therefore, in this article, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can explain and improve LLM-based AI systems and (2) how XAI techniques can be improved by using LLMs. We introduce 10 strategies, introducing the key techniques for each and discussing their associated challenges. We also provide case studies to demonstrate how to obtain and leverage explanations.

Large Language Models (LLMs) have brought significant advances across various NLP tasks through few-shot or zero-shot prompting, bypassing the need for parameter tuning. However, the "black-box" nature behind their massive parameter sizes increases the "hallucination" concerns, especially in high-stakes applications (e.g., healthcare), where decision mistakes can lead to severe consequences. In contrast, human decision-making relies on complex cognitive processes, such as the ability to sense and adaptively correct mistakes through conceptual understanding. Drawing inspiration from human cognition, we propose an innovative metacognitive approach CLEAR, to equip LLMs with capabilities for self-aware error identification and correction. Our framework constructs concept-specific sparse subnetworks that indicate decision processes. This provides a novel interface for model {intervention} after deployment. The benefits include: (i) at inference time, our metacognitive LLMs can self-consciously identify potential mispredictions with minimum human involvement, (ii) the model can self-correct its errors efficiently without additional tuning, and (iii) the correction procedure is not only self-explanatory but also user-friendly, enhancing model interpretability and accessibility. With these metacognitive features, our approach pioneers a new path toward the trustworthiness of LLMs.

In this paper, we address the limitations of existing text-to-image diffusion models in generating demographically fair results when given human-related descriptions. These models often struggle to disentangle the target language context from sociocultural biases, resulting in biased image generation. To overcome this challenge, we propose Fair Mapping, a flexible, model-agnostic, and lightweight approach that modifies a pre-trained text-to-image diffusion model by controlling the prompt to achieve fair image generation. One key advantage of our approach is its high efficiency. It only requires updating an additional linear network with few parameters at a low computational cost. By developing a linear network that maps conditioning embeddings into a debiased space, we enable the generation of relatively balanced demographic results based on the specified text condition. With comprehensive experiments on face image generation, we show that our method significantly improves image generation fairness with almost the same image quality compared to conventional diffusion models when prompted with descriptions related to humans. By effectively addressing the issue of implicit language bias, our method produces more fair and diverse image outputs.

Concept Bottleneck Models (CBMs) have garnered increasing attention due to their ability to provide concept-based explanations for black-box deep learning models while achieving high final prediction accuracy using human-like concepts. However, the training of current CBMs is heavily dependent on the precision and richness of the annotated concepts in the dataset. These concept labels are typically provided by experts, which can be costly and require significant resources and effort. Additionally, concept saliency maps frequently misalign with input saliency maps, causing concept predictions to correspond to irrelevant input features - an issue related to annotation alignment. To address these limitations, we propose a new framework called SSCBM (Semi-supervised Concept Bottleneck Model). Our SSCBM is suitable for practical situations where annotated data is scarce. By leveraging joint training on both labeled and unlabeled data and aligning the unlabeled data at the concept level, we effectively solve these issues. We proposed a strategy to generate pseudo labels and an alignment loss. Experiments demonstrate that our SSCBM is both effective and efficient. With only 10% labeled data, our model's concept and task accuracy on average across four datasets is only 2.44% and 3.93% lower, respectively, compared to the best baseline in the fully supervised learning setting.

The emergence of Vision-Language Models (VLMs) represents a significant advancement in integrating computer vision with Large Language Models (LLMs) to generate detailed text descriptions from visual inputs. Despite their growing importance, the security of VLMs, particularly against backdoor attacks, is under explored. Moreover, prior works often assume attackers have access to the original training data, which is often unrealistic. In this paper, we address a more practical and challenging scenario where attackers must rely solely on Out-Of-Distribution (OOD) data. We introduce VLOOD (Backdoor Vision-Language Models using Out-of-Distribution Data), a novel approach with two key contributions: (1) demonstrating backdoor attacks on VLMs in complex image-to-text tasks while minimizing degradation of the original semantics under poisoned inputs, and (2) proposing innovative techniques for backdoor injection without requiring any access to the original training data. Our evaluation on image captioning and visual question answering (VQA) tasks confirms the effectiveness of VLOOD, revealing a critical security vulnerability in VLMs and laying the foundation for future research on securing multimodal models against sophisticated threats.

The locate-then-edit paradigm has shown significant promise for knowledge editing (KE) in Large Language Models (LLMs). While previous methods perform well on single-hop fact recall tasks, they consistently struggle with multi-hop factual recall tasks involving newly edited knowledge. In this paper, leveraging tools in mechanistic interpretability, we first identify that in multi-hop tasks, LLMs tend to retrieve knowledge with implicit subject information from deeper MLP layers, unlike single-hop tasks, which rely on shallow layers. This distinction explains the poor performance of current methods in multi-hop queries, as they primarily focus on editing shallow layers with single-hop edit prompts, leaving deeper layers unchanged. To address this, we propose IFMET, a novel locate-then-edit KE approach designed to edit both shallow and deep MLP layers. Beyond single-hop editing prompts, IFMET further incorporates multi-hop editing prompts to locate and modify knowledge across different stages of reasoning. Experimental results demonstrate that IFMET significantly improves performance on multi-hop factual recall tasks, overcoming the limitations of previous locate-then-edit methods.

Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most previous studies focused on cases where the data, including concepts, are clean. In many scenarios, we always need to remove/insert some training data or new concepts from trained CBMs due to different reasons, such as privacy concerns, data mislabelling, spurious concepts, and concept annotation errors. Thus, the challenge of deriving efficient editable CBMs without retraining from scratch persists, particularly in large-scale applications. To address these challenges, we propose Editable Concept Bottleneck Models (ECBMs). Specifically, ECBMs support three different levels of data removal: concept-label-level, concept-level, and data-level. ECBMs enjoy mathematically rigorous closed-form approximations derived from influence functions that obviate the need for re-training. Experimental results demonstrate the efficiency and effectiveness of our ECBMs, affirming their adaptability within the realm of CBMs.

Recent advancements in autonomous driving have seen a paradigm shift towards end-to-end learning paradigms, which map sensory inputs directly to driving actions, thereby enhancing the robustness and adaptability of autonomous vehicles. However, these models often sacrifice interpretability, posing significant challenges to trust, safety, and regulatory compliance. To address these issues, we introduce DRIVE – Dependable Robust Interpretable Visionary Ensemble Framework in Autonomous Driving, a comprehensive framework designed to improve the dependability and stability of explanations in end-to-end unsupervised autonomous driving models. Our work specifically targets the inherent instability problems observed in the Driving through the Concept Gridlock (DCG) model, which undermine the trustworthiness of its explanations and decisionmaking processes. We define four key attributes of DRIVE: consistent interpretability, stable interpretability, consistent output, and stable output. These attributes collectively ensure that explanations remain reliable and robust across different scenarios and perturbations. Through extensive empirical evaluations, we demonstrate the effectiveness of our framework in enhancing the stability and dependability of explanations, thereby addressing the limitations of current models. Our contributions include an in-depth analysis of the dependability issues within the DCG model, a rigorous definition of DRIVE with its fundamental properties, a framework to implement DRIVE, and novel metrics for evaluating the dependability of concept-based explainable autonomous driving models. These advancements lay the groundwork for the development of more reliable and trusted autonomous driving systems, paving the way for their broader acceptance and deployment in real-world applications. “We can only see a short distance ahead, but we can see plenty there that needs to be done.” – Alan Turing

Multimodal learning benefits from multiple modal information, and each learned modal representations can be divided into uni-modal that can be learned from uni-modal training and paired-modal features that can be learned from cross-modal interaction. Building on this perspective, we propose a partitioner-guided modal learning framework, PgM, which consists of the modal partitioner, uni-modal learner, paired-modal learner, and uni-paired modal decoder. Modal partitioner segments the learned modal representation into uni-modal and paired-modal features. Modal learner incorporates two dedicated components for uni-modal and paired-modal learning. Uni-paired modal decoder reconstructs modal representation based on uni-modal and paired-modal features. PgM offers three key benefits: 1) thorough learning of uni-modal and paired-modal features, 2) flexible distribution adjustment for uni-modal and paired-modal representations to suit diverse downstream tasks, and 3) different learning rates across modalities and partitions. Extensive experiments demonstrate the effectiveness of PgM across four multimodal tasks and further highlight its transferability to existing models. Additionally, we visualize the distribution of uni-modal and paired-modal features across modalities and tasks, offering insights into their respective contributions.

The domain of time series forecasting has gained significant attention due to its critical applications in multimedia-rich web traffic (including video streaming workloads and dynamic content delivery) and cross-platform advertisement click predictions, which are essential for web operations planning. While models like TimeSieve have demonstrated strong capabilities in predicting web visitation metrics, they suffer from critical unfaithfulness issues, including sensitivity to random seeds, input noise, layer noise, and parametric perturbations. To address these limitations, we propose Faithful TimeSieve (FTS), an enhanced framework designed to improve prediction reliability and robustness. Our approach systematically detects and mitigates unfaithfulness in TimeSieve, significantly enhancing its stability and consistency. Experimental results demonstrate that FTS substantially improves the model's faithfulness, setting a new standard for temporal forecasting methods. This advancement not only increases TimeSieve's reliability but also contributes to more robust temporal modeling, particularly crucial for web traffic forecasting where prediction accuracy directly impacts operational decisions. Our work thus represents a significant step toward more dependable time series predictions in web-related applications.

Understanding the internal mechanisms of transformer-based language models remains challenging. Mechanistic interpretability based on circuit discovery aims to reverse engineer neural networks by analyzing their internal processes at the level of computational subgraphs. In this paper, we revisit existing gradient-based circuit identification methods and find that their performance is either affected by the zero-gradient problem or saturation effects, where edge attribution scores become insensitive to input changes, resulting in noisy and unreliable attribution evaluations for circuit components. To address the saturation effect, we propose Edge Attribution Patching with GradPath (EAP-GP), EAP-GP introduces an integration path, starting from the input and adaptively following the direction of the difference between the gradients of corrupted and clean inputs to avoid the saturated region. This approach enhances attribution reliability and improves the faithfulness of circuit identification. We evaluate EAP-GP on 6 datasets using GPT-2 Small, GPT-2 Medium, and GPT-2 XL. Experimental results demonstrate that EAP-GP outperforms existing methods in circuit faithfulness, achieving improvements up to 17.7\%. Comparisons with manually annotated ground-truth circuits demonstrate that EAP-GP achieves precision and recall comparable to or better than previous approaches, highlighting its effectiveness in identifying accurate circuits.

As a potential IoT technology for future networks, Ambient IoT (A-IoT) has entered the standardization process in Third Generation Partnership Project (3GPP). In A-IoT, Forward Error Correction (FEC)-Miller concatenated coding is emerging as a promising coding mechanism due to its advantages in link performance and time synchronization. This concatenated mechanism necessitates the use of Miller soft decoding before FEC decoding. However, it is difficult to design a unified Miller soft decoding approach in A-IoT. The reason is that, the soft decoding approach is closely associated with the receiver detection approaches, such as envelope detectors or amplitude/phase detectors. Owing to the diversity of A-IoT devices/readers, hardware complexities of different receivers vary significantly, thereby resulting in disparate signal detecting and decoding capabilities. To address this challenge, this paper considers three typical A-IoT receivers with different hardware complexities, proposes Miller soft decoding algorithms in Miller-FEC concatenated decoding for each receiver respectively, and derives closed-form expressions of Log-Likelihood Ratio (LLR). Finally, link-level simulations are conducted to validate the effectiveness of the proposed algorithms across different receivers.

Currently, attention mechanism has become a standard fixture in most state-of-the-art natural language processing (NLP) models, not only due to the outstanding performance it could gain but also due to plausible innate explanations for the behaviors of neural architectures it provides, which is notoriously difficult to analyze. However, recent studies show that attention is unstable against randomness and perturbations during training or testing, such as random seeds and slight perturbation of embedding vectors, which impedes it from becoming a faithful explanation tool. Thus, a natural question is whether we can find some substitute for the current attention that is more stable and could keep the most important characteristics of explanation and prediction of attention. In this paper, to resolve the problem, we provide a rigorous definition of such alternate namely SEAT (Stable andExplainableAttention). Specifically, a SEAT should have the following three properties: (1) Its prediction distribution is enforced to be close to the distribution based on the vanilla attention; (2) Its top-$k$indices have large overlaps with those of the vanilla attention; (3) It is robust w.r.t perturbations, i.e., any slight perturbation on SEAT will not change the prediction distribution too much, which implicitly indicates that it is stable to randomness and perturbations. To further improve the interpretability stability against perturbations, based on SEAT we provide another definition called SEAT++. Then we propose a method to get a SEAT++, which could be considered an ad hoc modification for canonical attention. Finally, through intensive experiments on various datasets, we compare our SEAT and SEAT++ with other baseline methods using RNN, BiLSTM, and BERT architectures via six different evaluation metrics for model interpretation, stability, and accuracy. Results show that SEAT and SEAT++ are more stable against different perturbations and randomness while also keeping the explainability of attention, which indicates they provide more faithful explanations. Moreover, compared with vanilla attention, there is almost no utility (accuracy) degradation for SEAT and SEAT++.

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities.However, the true effectiveness of these methods is unclear.In this work, we delve into the limitations of fine-tuning-based unlearning through activation patching and parameter restoration experiments.Our findings reveal that these methods alter the model's knowledge retrieval process, providing further evidence that they do not genuinely erase the problematic knowledge embedded in the model parameters.Instead, the coefficients generated by the MLP components in the model's final layer are the primary contributors to these seemingly positive unlearning effects, playing a crucial role in controlling the model's behaviors.Furthermore, behavioral tests demonstrate that this unlearning mechanism inevitably impacts the global behavior of the models, affecting unrelated knowledge or capabilities.The code is released at https://github.com/yihuaihong/ Dissecting-FT-Unlearning.

Deep learning models for NLP tasks are prone to variants of privacy attacks.To prevent privacy leakage, researchers have investigated word-level perturbations, relying on the formal guarantees of differential privacy (DP) in the embedding space.However, many existing approaches either achieve unsatisfactory performance in the high privacy regime when using the Laplacian or Gaussian mechanism, or resort to weaker relaxations of DP that are inferior to the canonical DP in terms of privacy strength.This raises the question of whether a new method for private word embedding can be designed to overcome these limitations.In this paper, we propose a novel private embedding method called the high dimensional truncated Laplacian mechanism.Specifically, we introduce a non-trivial extension of the truncated Laplacian mechanism, which was previously only investigated in one-dimensional space cases.Theoretically, we show that our method has a lower variance compared to the previous private word embedding methods.To further validate its effectiveness, we conduct comprehensive experiments on private embedding and downstream tasks using three datasets.Remarkably, even in the high privacy regime, our approach only incurs a slight decrease in utility compared to the non-private scenario.

The demand for transparency in healthcare and finance has led to interpretable machine learning (IML) models, notably the concept bottleneck models (CBMs), valued for their potential in performance and insights into deep neural networks. However, CBM's reliance on manually annotated data poses challenges. Label-free CBMs have emerged to address this, but they remain unstable, affecting their faithfulness as explanatory tools. To address this issue of inherent instability, we introduce a formal definition for an alternative concept called the Faithful Vision-Language Concept (FVLC) model. We present a methodology for constructing an FVLC that satisfies four critical properties. Our extensive experiments on four benchmark datasets using Label-free CBM model architectures demonstrate that our FVLC outperforms other baselines regarding stability against input and concept set perturbations. Our approach incurs minimal accuracy degradation compared to the vanilla CBM, making it a promising solution for reliable and faithful model interpretation.

Vision Transformers (ViTs) have achieved state-of-the-art performance for various vision tasks. One reason behind the success lies in their ability to provide plausible innate explanations for the behavior of neural architectures. However, ViTs suffer from issues with explanation faithfulness, as their focal points are fragile to adversarial attacks and can be easily changed with even slight perturbations on the input image. In this paper, we propose a rigorous approach to mitigate these issues by introducing Faithful ViTs (FViTs). Briefly speaking, an FViT should have the following two properties: (1) The top-$k$ indices of its self-attention vector should remain mostly unchanged under input perturbation, indicating stable explanations; (2) The prediction distribution should be robust to perturbations. To achieve this, we propose a new method called Denoised Diffusion Smoothing (DDS), which adopts randomized smoothing and diffusion-based denoising. We theoretically prove that processing ViTs directly with DDS can turn them into FViTs. We also show that Gaussian noise is nearly optimal for both $\ell_2$ and $\ell_\infty$-norm cases. Finally, we demonstrate the effectiveness of our approach through comprehensive experiments and evaluations. Results show that FViTs are more robust against adversarial attacks while maintaining the explainability of attention, indicating higher faithfulness.

Is the Text to Motion model robust? Recent advancements in Text to Motion models primarily stem from more accurate predictions of specific actions. However, the text modality typically relies solely on pre-trained Contrastive Language-Image Pretraining (CLIP) models. Our research has uncovered a significant issue with the text-tomotion model: its predictions often exhibit inconsistent outputs, resulting in vastly different or even incorrect poses when presented with semantically similar or identical text inputs. In this paper, we undertake an analysis to elucidate the underlying causes of this instability, establishing a clear link between the unpredictability of model outputs and the erratic attention patterns of the text encoder module. Consequently, we introduce a formal framework aimed at addressing this issue, which we term the Stable Text-to-Motion Framework (SATO). SATO consists of three modules, each dedicated to stable attention, stable prediction, and maintaining a balance between accuracy and robustness trade-off. We present a methodology for constructing an SATO that satisfies the stability of attention and prediction. To verify the stability of the model, we introduced a new textual synonym perturbation dataset based on HumanML3D and KIT-ML. Results show that SATO is significantly more stable against synonyms and other slight perturbations while keeping its high accuracy performance. Codes and models are released at

The lack of interpretability in the field of medical image analysis has significant ethical and legal implications. Existing interpretable methods in this domain encounter several challenges, including dependency on specific models, difficulties in understanding and visualization, and issues related to efficiency. To address these limitations, we propose a novel framework called Med-MICN (Medical Multi-dimensional Interpretable Concept Network). Med-MICN provides interpretability alignment for various angles, including neural symbolic reasoning, concept semantics, and saliency maps, which are superior to current interpretable methods. Its advantages include high prediction accuracy, interpretability across multiple dimensions, and automation through an end-to-end concept labeling process that reduces the need for extensive human training effort when working with new datasets. To demonstrate the effectiveness and interpretability of Med-MICN, we apply it to four benchmark datasets and compare it with baselines. The results clearly demonstrate the superior performance and interpretability of our Med-MICN.

In this paper, we revisit the problem of Differentially Private Stochastic Convex Optimization (DP-SCO) and provide excess population risks for some special classes of functions that are faster than the previous results of general convex and strongly convex functions. In the first part of the paper, we study the case where the population risk function satisfies the Tysbakov Noise Condition (TNC) with some parameter $\theta>1$. Specifically, we first show that under some mild assumptions on the loss functions, there is an algorithm whose output could achieve an upper bound of $\tilde{O}((\frac{1}{\sqrt{n}}+\frac{d}{n\epsilon})^\frac{\theta}{\theta-1}) $ and $\tilde{O}((\frac{1}{\sqrt{n}}+\frac{\sqrt{d\log(1/\delta)}}{n\epsilon})^\frac{\theta}{\theta-1})$ for $\epsilon$-DP and $(\epsilon, \delta)$-DP, respectively when $\theta\geq 2$, where $n$ is the sample size and $d$ is the dimension of the space. Then we address the inefficiency issue, improve the upper bounds by $\text{Poly}(\log n)$ factors and extend to the case where $\theta\geq \bar{\theta}>1$ for some known $\bar{\theta}$. Next, we show that the excess population risk of population functions satisfying TNC with parameter $\theta\geq 2$ is always lower bounded by $\Omega((\frac{d}{n\epsilon})^\frac{\theta}{\theta-1}) $ and $\Omega((\frac{\sqrt{d\log(1/\delta)}}{n\epsilon})^\frac{\theta}{\theta-1})$ for $\epsilon$-DP and $(\epsilon, \delta)$-DP, respectively, which matches our upper bounds. In the second part, we focus on a special case where the population risk function is strongly convex. Unlike the previous studies, here we assume the loss function is non-negative and the optimal value of population risk is sufficiently small. With these additional assumptions, we propose a new method whose output could achieve an upper bound of $O(\frac{d\log(1/\delta)}{n^2\epsilon^2}+\frac{1}{n^{\tau}})$ and $O(\frac{d^2}{n^2\epsilon^2}+\frac{1}{n^{\tau}})$ for any $\tau> 1$ in $(\epsilon,\delta)$-DP and $\epsilon$-DP model respectively if the sample size $n$ is sufficiently large. These results circumvent their corresponding lower bounds in (Feldman et al., 2020) for general strongly convex functions. Finally, we conduct experiments of our new methods on real-world data. Experimental results also provide new insights into established theories.

In this paper, we study the (sparse) Generalized Eigenvalue Problem (GEP), which arises in a number of modern statistical learning models, such as principal component analysis (PCA), canonical correlation analysis (CCA), Fisher's discriminant analysis (FDA) and sliced inverse regression (SIR). We provide the first study on GEP in the differential privacy (DP) model under both deterministic and stochastic settings. In the low dimensional case, we provide a$\rho$-Concentrated DP (CDP) method namely DP-Rayleigh Flow and show if the initial vector is close enough to the optimal vector, its output has an$\ell _{2}$-norm estimation error of$\tilde{O}(\frac{d}{n}+\frac{d}{n^{2}\rho })$(under some mild assumptions), where$d$is the dimension and$n$is the sample size. Next, we discuss how to find such an initial parameter privately. In the high dimensional sparse case where$d\gg n$, we propose the DP-Truncated Rayleigh Flow method whose output could achieve an error of$\tilde{O}(\frac{s\log d}{n}+\frac{s\log d}{n^{2}\rho })$for various statistical models, where$s$is the sparsity of the underlying parameter. Moreover, we show that these errors in the stochastic setting are optimal up to a factor of$\text{Poly}(\log n)$by providing the lower bounds of PCA and SIR under the statistical setting and in the CDP model. Finally, to give a separation between$\epsilon$-DP and$\rho$-CDP for GEP, we also provide the lower bound$\Omega (\frac{d}{n}+\frac{d^{2}}{n^{2}\epsilon ^{2}})$and$\Omega (\frac{s\log d}{n}+\frac{s^{2}\log ^{2} d}{n^{2}\epsilon ^{2}})$of private minimax risk for PCA, under the statistical setting and$\epsilon$-DP model, in low and high dimensional sparse case respectively. Finally, extensive experiments on both synthetic and real-world data support our previous theoretical analysis.

Attention mechanism has become a standard fixture in many state-of-the-art natural language processing (NLP) models, not only due to its outstanding performance, but also because it provides plausible innate explanations for neural architectures. However, recent studies show that attention is unstable against randomness and perturbations during training or testing, such as random seeds and slight perturbation of embeddings, which impedes it from being a faithful explanation tool. Thus, a natural question is whether we can find an alternative to vanilla attention, which is more stable and could keep the key characteristics of the explanation. In this paper, we provide a rigorous definition of such an attention method named SEAT (Stable and Explainable ATtention). Specifically, SEAT has the following three properties: (1) Its prediction distribution is close to the prediction of the vanilla attention; (2) Its top-k indices largely overlap with those of the vanilla attention; (3) It is robust w.r.t perturbations, i.e., any slight perturbation on SEAT will not change the attention and prediction distribution too much, which implicitly indicates that it is stable to randomness and perturbations. Furthermore, we propose an optimization method for obtaining SEAT, which could be considered as revising the vanilla attention. Finally, through intensive experiments on various datasets, we compare our SEAT with other baseline methods using RNN, BiLSTM and BERT architectures, with different evaluation metrics on model interpretation, stability and accuracy. Results show that, besides preserving the original explainability and model performance, SEAT is more stable against input perturbations and training randomness, which indicates it is a more faithful explanation.

In this paper we study the (sparse) Generalized Eigenvalue Problem (GEP), which arises in a number of modern statistical learning models, such as principal component analysis (PCA), canonical correlation analysis (CCA), Fisher’s discriminant analysis (FDA) and sliced inverse regression (SIR). We provide the first study on GEP in the differential privacy (DP) model under both deterministic and stochastic settings. In the low dimensional case, we provide a $\rho$-Concentrated DP (CDP) method namely DP-Rayleigh Flow and show if the initial vector is close enough to the optimal vector, its output has an $\ell_2$-norm estimation error of $\tilde{O}(\frac{d}{n}+\frac{d}{n^2\rho})$ (under some mild assumptions), where $d$ is the dimension and $n$ is the sample size. Next, we discuss how to find such a initial parameter privately. In the high dimensional sparse case where $d\gg n$, we propose the DP-Truncated Rayleigh Flow method whose output could achieve an error of $\tilde{O}(\frac{s\log d}{n}+\frac{s\log d}{n^2\rho})$ for various statistical models, where $s$ is the sparsity of the underlying parameter.Moreover, we show that these errors in the stochastic setting are optimal up to a factor of $\mathrm{Poly}(\log n)$ by providing the lower bounds of PCA and SIR under statistical setting and in the CDP model. Finally, to give a separation between $\epsilon$-DP and $\rho$-CDP for GEP, we also provide the lower bound $\Omega(\frac{d}{n}+\frac{d^2}{n^2\epsilon^2})$ and $\Omega(\frac{s\log d}{n}+\frac{s^2\log^2 d}{n^2\epsilon^2})$ of private minimax risk for PCA, under the statistical setting and $\epsilon$-DP model, in low and high dimensional sparse case respectively.

(Gradient) Expectation Maximization (EM) is a widely used algorithm for estimating the maximum likelihood of mixture models or incomplete data problems. A major challenge facing this popular technique is how to effectively preserve the privacy of sensitive data. Previous research on this problem has already lead to the discovery of some Differentially Private (DP) algorithms for (Gradient) EM. However, unlike in the non-private case, existing techniques are not yet able to provide finite sample statistical guarantees. To address this issue, we propose in this paper the first DP version of Gradient EM algorithm with statistical guarantees. Specifically, we first propose a new mechanism for privately estimating the mean of a heavy-tailed distribution, which significantly improves a previous result in [25], and it could be extended to the local DP model, which has not been studied before. Next, we apply our general framework to three canonical models: Gaussian Mixture Model (GMM), Mixture of Regressions Model (MRM) and Linear Regression with Missing Covariates (RMC). Specifically, for GMM in the DP model, our estimation error is near optimal in some cases. For the other two models, we provide the first result on finite sample statistical guarantees. Our theory is supported by thorough numerical experiments on both real-world data and synthetic data.

In this paper, we study the problem of estimating smooth Generalized Linear Models (GLMs) in the Non-interactive Local Differential Privacy (NLDP) model. Unlike its classical setting, our model allows the server to access additional public but unlabeled data. In the first part of the paper, we focus on GLMs. Specifically, we first consider the case where each data record is i.i.d. sampled from a zero-mean multivariate Gaussian distribution. Motivated by the Stein's lemma, we present an $(\epsilon, \delta)$-NLDP algorithm for GLMs. Moreover, the sample complexity of public and private data for the algorithm to achieve an $\ell_2$-norm estimation error of $\alpha$ (with high probability) is ${O}(p \alpha^{-2})$ and $\tilde{O}(p^3\alpha^{-2}\epsilon^{-2})$ respectively, where $p$ is the dimension of the feature vector. This is a significant improvement over the previously known exponential or quasi-polynomial in $\alpha^{-1}$, or exponential in $p$ sample complexities of GLMs with no public data. Then we consider a more general setting where each data record is i.i.d. sampled from some sub-Gaussian distribution with bounded $\ell_1$-norm. Based on a variant of Stein's lemma, we propose an $(\epsilon, \delta)$-NLDP algorithm for GLMs whose sample complexity of public and private data to achieve an $\ell_\infty$-norm estimation error of $\alpha$ is ${O}(p^2\alpha^{-2})$ and $\tilde{O}(p^2\alpha^{-2}\epsilon^{-2})$ respectively, under some mild assumptions and if $\alpha$ is not too small i.e., $\alpha\geq \Omega(\frac{1}{\sqrt{p}})$). In the second part of the paper, we extend our idea to the problem of estimating non-linear regressions and show similar results as in GLMs for both multivariate Gaussian and sub-Gaussian cases. Finally, we demonstrate the effectiveness of our algorithms through experiments on both synthetic and real-world datasets. To our best knowledge, this is the first paper showing the existence of efficient and effective algorithms for GLMs and non-linear regressions in the NLDP model with unlabeled public data.

In this paper, we revisit the problem of Differentially Private Stochastic Convex Optimization (DP-SCO) and provide excess population risks for some special classes of functions that are faster than the previous results of general convex and strongly convex functions. In the first part of the paper, we study the case where the population risk function satisfies the Tysbakov Noise Condition (TNC) with some parameter $\theta>1$. Specifically, we first show that under some mild assumptions on the loss functions, there is an algorithm whose output could achieve an upper bound of $\tilde{O}((\frac{1}{\sqrt{n}}+\frac{d}{n\epsilon})^\frac{\theta}{\theta-1}) $ and $\tilde{O}((\frac{1}{\sqrt{n}}+\frac{\sqrt{d\log(1/\delta)}}{n\epsilon})^\frac{\theta}{\theta-1})$ for $\epsilon$-DP and $(\epsilon, \delta)$-DP, respectively when $\theta\geq 2$, here $n$ is the sample size and $d$ is the dimension of the space. Then we address the inefficiency issue, improve the upper bounds by $\text{Poly}(\log n)$ factors and extend to the case where $\theta\geq \bar{\theta}>1$ for some known $\bar{\theta}$. Next we show that the excess population risk of population functions satisfying TNC with parameter $\theta\geq 2$ is always lower bounded by $\Omega((\frac{d}{n\epsilon})^\frac{\theta}{\theta-1}) $ and $\Omega((\frac{\sqrt{d\log(1/\delta)}}{n\epsilon})^\frac{\theta}{\theta-1})$ for $\epsilon$-DP and $(\epsilon, \delta)$-DP, respectively, which matches our upper bounds. In the second part, we focus on a special case where the population risk function is strongly convex. Unlike the previous studies, here we assume the loss function is non-negative and the optimal value of population risk is sufficiently small. With these additional assumptions, we propose a new method whose output could achieve an upper bound of $O(\frac{d\log(1/\delta)}{n^2\epsilon^2}+\frac{1}{n^{\tau}})$ and $O(\frac{d^2}{n^2\epsilon^2}+\frac{1}{n^{\tau}})$ for any $\tau> 1$ in $(\epsilon,\delta)$-DP and $\epsilon$-DP model respectively if the sample size $n$ is sufficiently large. These results circumvent their corresponding lower bounds in (Feldman et al., 2020) for general strongly convex functions. Finally, we conduct experiments of our new methods on real world data. Experimental results also provide new insights into established theories.

As one of the most fundamental problems in machine learning, statistics and differential privacy, Differentially Private Stochastic Convex Optimization (DP-SCO) has been extensively studied in recent years. However, most of the previous work can only handle either regular data distributions or irregular data in the low dimensional space case. To better understand the challenges arising from irregular data distributions, in this paper we provide the first study on the problem of DP-SCO with heavy-tailed data in the high dimensional space. In the first part we focus on the problem over some polytope constraint (such as the l1-norm ball). We show that if the loss function is smooth and its gradient has bounded second order moment, it is possible to get a (high probability) error bound (excess population risk) of Õ(log d/(nε)1/3) in the ε-DP model, where n is the sample size and d is the dimension of the underlying space. Next, for LASSO, if the data distribution has bounded fourth-order moments, we improve the bound to Õ(log d/(nε)2/5) in the $(ε, δ)-DP model. In the second part of the paper, we study sparse learning with heavy-tailed data. We first revisit the sparse linear model and propose a truncated DP-IHT method whose output could achieve an error of Õ ((s*2 log2d)/nε), where s* is the sparsity of the underlying parameter. Then we study a more general problem over the sparsity (i.e., l0-norm) constraint, and show that it is possible to achieve an error of Õ((s*3/2 log d)/nε), which is also near optimal up to a factor of Õ(√s*), if the loss function is smooth and strongly convex.

3D-MIMO, using two dimensional antenna array at base station, demonstrates promising throughput gain over conventional antenna system during recent academic and industry studies. To realize the performance gain, accurate channel state information (CSI) feedback is one essential aspect. One effective way to obtain this CSI is taking advantage of channel reciprocity between uplink and downlink in TDD system. This paper analyzes the uplink pilot contamination problem in practical TDD LTE system using a novel pilot contamination model, besides, pilot contamination elimination methods in terms of increasing pilot power and reducing pilot collision probability are evaluated. The simulation results show that system performance degradation is less than 21% considering the practical pilot contamination, which still outperform the traditional 2D-MIMO system. Moreover, about 15% performance gain could be benefit from pilot contamination reduction approaches.