Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models

• URL: http://arxiv.org/abs/2504.03714v2
• Date: Mon, 07 Jul 2025 04:11:47 GMT
• Title: Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models
• Authors: Runpeng Dai, Run Yang, Fan Zhou, Hongtu Zhu,
• Abstract summary: Large Language Models (LLMs) and Vision-Language Models (VLMs) have achieved impressive performance across a wide range of tasks.<n>In this study, we seek to pinpoint the sources of this fragility by identifying parameters and input dimensions that are susceptible to such perturbations.<n>We propose a stability measure called textbfFI, textbfFirst order local textbfInfluence, which is rooted in information geometry and quantifies the sensitivity of individual parameter and input dimensions.
• Score: 13.216398753024182
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) have achieved impressive performance across a wide range of tasks, yet they remain vulnerable to carefully crafted perturbations. In this study, we seek to pinpoint the sources of this fragility by identifying parameters and input dimensions (pixels or token embeddings) that are susceptible to such perturbations. To this end, we propose a stability measure called \textbf{FI}, \textbf{F}irst order local \textbf{I}nfluence, which is rooted in information geometry and quantifies the sensitivity of individual parameter and input dimensions. Our extensive analysis across LLMs and VLMs (from 1.5B to 13B parameters) reveals that: (I) A small subset of parameters or input dimensions with high FI values disproportionately contribute to model brittleness. (II) Mitigating the influence of these vulnerable parameters during model merging leads to improved performance.

Related papers

• Contrastive Normalizing Flows for Uncertainty-Aware Parameter Estimation [0.0]
  Estimating physical parameters from data is a crucial application of machine learning (ML) in the physical sciences.<n>We introduce a novel approach based on Contrastive Normalizing Flows (CNFs), which achieves top performance on the HiggsML Uncertainty Challenge dataset.
  arXiv  Detail & Related papers  (2025-05-13T16:14:34Z)
• Towards Robust LLMs: an Adversarial Robustness Measurement Framework [0.0]
  Large Language Models (LLMs) remain vulnerable to adversarial perturbations, undermining their reliability in high-stakes applications. We adapt the Robustness Measurement and Assessment framework to quantify LLM resilience against adversarial inputs without requiring access to model parameters. Our work provides a systematic methodology to assess LLM robustness, advancing the development of more reliable language models for real-world deployment.
  arXiv  Detail & Related papers  (2025-04-24T16:36:19Z)
• Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge [0.0]
  Large Language Models (LLMs) have revolutionized artificial intelligence, driving advancements in machine translation, summarization, and conversational agents.<n>Recent studies indicate that LLMs remain vulnerable to adversarial attacks designed to elicit biased responses.<n>This work proposes a scalable benchmarking framework to evaluate LLM robustness against adversarial bias elicitation.
  arXiv  Detail & Related papers  (2025-04-10T16:00:59Z)
• Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models [55.46269953415811]
  We identify ToM-sensitive parameters and show that perturbing as little as 0.001% of these parameters significantly degrades ToM performance.<n>Our results have implications for enhancing model alignment, mitigating biases, and improving AI systems designed for human interaction.
  arXiv  Detail & Related papers  (2025-04-05T17:45:42Z)
• Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions [49.546479320670464]
  This paper introduces specialized metrics for benchmarking the robustness of segmentation models under localized corruptions.<n>We propose region-aware multi-attack adversarial analysis, a method that enables a deeper understanding of model robustness against adversarial perturbations applied to specific regions.<n>The results reveal that models respond to these two types of threats differently.
  arXiv  Detail & Related papers  (2025-04-02T11:37:39Z)
• Breaking Focus: Contextual Distraction Curse in Large Language Models [68.4534308805202]
  We investigate a critical vulnerability in Large Language Models (LLMs)<n>This phenomenon arises when models fail to maintain consistent performance on questions modified with semantically coherent but irrelevant context.<n>We propose an efficient tree-based search methodology to automatically generate CDV examples.
  arXiv  Detail & Related papers  (2025-02-03T18:43:36Z)
• Explainability of Point Cloud Neural Networks Using SMILE: Statistical Model-Agnostic Interpretability with Local Explanations [0.0]
  This study explores the implementation of SMILE, a novel explainability method originally designed for deep neural networks, on point cloud-based models. The approach demonstrates superior performance in terms of fidelity loss, R2 scores, and robustness across various kernel widths, perturbation numbers, and clustering configurations. The study further identifies dataset biases in the classification of the 'person' category, emphasizing the necessity for more comprehensive datasets in safety-critical applications.
  arXiv  Detail & Related papers  (2024-10-20T12:13:59Z)
• SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models [85.67096251281191]
  We present an innovative approach to model fusion called zero-shot Sparse MIxture of Low-rank Experts (SMILE) construction. SMILE allows for the upscaling of source models into an MoE model without extra data or further training. We conduct extensive experiments across diverse scenarios, such as image classification and text generation tasks, using full fine-tuning and LoRA fine-tuning.
  arXiv  Detail & Related papers  (2024-08-19T17:32:15Z)
• Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack [12.647669152300871]
  We study the complexities of adversarial attack algorithms, dissecting the adversarial process into two critical phases: the Directional Supervision Process (DSP) and the Directional Optimization Process (DOP) The impact of models on adversarial efficacy is often overlooked in current research, leading to neglect of DSP. We propose that under certain conditions, fine-tuning model parameters can significantly enhance the quality of DSP.
  arXiv  Detail & Related papers  (2024-08-14T17:51:15Z)
• Low-rank finetuning for LLMs: A fairness perspective [54.13240282850982]
  Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models. This paper investigates the effectiveness of these methods in capturing the shift of fine-tuning datasets from the initial pre-trained data distribution. We show that low-rank fine-tuning inadvertently preserves undesirable biases and toxic behaviors.
  arXiv  Detail & Related papers  (2024-05-28T20:43:53Z)
• Advancing the Robustness of Large Language Models through Self-Denoised Smoothing [50.54276872204319]
  Large language models (LLMs) have achieved significant success, but their vulnerability to adversarial perturbations has raised considerable concerns. We propose to leverage the multitasking nature of LLMs to first denoise the noisy inputs and then to make predictions based on these denoised versions. Unlike previous denoised smoothing techniques in computer vision, which require training a separate model to enhance the robustness of LLMs, our method offers significantly better efficiency and flexibility.
  arXiv  Detail & Related papers  (2024-04-18T15:47:00Z)
• The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness [50.52507648690234]
  Federated learning has the risk of skewing fine-tuning features and compromising the robustness of the model. We introduce three robustness indicators and conduct experiments across diverse robust datasets. Our approach markedly enhances the robustness across diverse scenarios, encompassing various parameter-efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2024-01-25T09:18:51Z)
• RoAST: Robustifying Language Models via Adversarial Perturbation with Selective Training [105.02614392553198]
  We propose Robustifying LMs via Adversarial perturbation with Selective Training (RoAST) RoAST incorporates two important sources for the model robustness, robustness on the perturbed inputs and generalizable knowledge in pre-trained LMs. We demonstrate the effectiveness of RoAST compared to state-of-the-art fine-tuning methods on six different types of LMs.
  arXiv  Detail & Related papers  (2023-12-07T04:23:36Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• Fairness Increases Adversarial Vulnerability [50.90773979394264]
  This paper shows the existence of a dichotomy between fairness and robustness, and analyzes when achieving fairness decreases the model robustness to adversarial samples. Experiments on non-linear models and different architectures validate the theoretical findings in multiple vision domains. The paper proposes a simple, yet effective, solution to construct models achieving good tradeoffs between fairness and robustness.
  arXiv  Detail & Related papers  (2022-11-21T19:55:35Z)
• Measure and Improve Robustness in NLP Models: A Survey [23.515869499536237]
  robustness has been separately explored in applications like vision and NLP, with various definitions, evaluation and mitigation strategies in multiple lines of research. We first connect multiple definitions of robustness, then unify various lines of work on identifying robustness failures and evaluating models' robustness. We present mitigation strategies that are data-driven, model-driven, and inductive-prior-based, with a more systematic view of how to effectively improve robustness in NLP models.
  arXiv  Detail & Related papers  (2021-12-15T18:02:04Z)
• Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption [40.76024057426747]
  We propose an indicator to measure the robustness of neural network parameters by exploiting their vulnerability via parameter corruption. For practical purposes, we give a gradient-based estimation, which is far more effective than random corruption trials.
  arXiv  Detail & Related papers  (2020-06-10T02:29:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.