AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps

• URL: http://arxiv.org/abs/2605.16905v1
• Date: Sat, 16 May 2026 09:36:58 GMT
• Title: AIM: Adversarial Information Masking for Faithfulness Evaluation of Saliency Maps
• Abstract summary: Post-hoc saliency methods are widely used to interpret deep neural networks.<n> Existing evaluations mask features according to saliency-induced feature ordering and measure performance degradation.<n>We propose Adrial Information Masking (AIM), a saliency-guided adversarial feature replacement framework for evaluating both saliency-map faithfulness and masking-operator reliability.
• Score: 0.9940728137241214
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Post-hoc saliency methods are widely used to interpret deep neural networks, but their faithfulness is difficult to evaluate reliably. Existing evaluations mask features according to saliency-induced feature ordering and measure performance degradation, but this degradation can be confounded by the masking operator: zero masking may create out-of-distribution artifacts, while interpolation-based masking may preserve residual predictive information. We propose Adversarial Information Masking (AIM), a saliency-guided adversarial feature replacement framework for evaluating both saliency-map faithfulness and masking-operator reliability. AIM replaces selected features with values from an adversarial counterpart of the input and compares degradation under complementary masking orders. We assess reliability using random-attribution bias and stability of explanation-method faithfulness rankings. Experiments on image, audio, and EEG tasks suggest that AIM reduces masking-induced bias compared with zero and interpolation-based masking, while revealing modality-dependent differences between signed and unsigned attributions.

Related papers

• CORE: Context-Robust Remasking for Diffusion Language Models [51.59514489363897]
  We propose Context-Robust Remasking (CORE), a training-free framework for inference-time revision.<n>Rather than trusting static token probabilities, CORE identifies context-brittle tokens by probing their sensitivity to targeted masked-context perturbations.<n>On LLaDA-8B-Base, CORE delivers consistent improvements across reasoning and code benchmarks, outperforming compute-matched baselines and improving MBPP by up to 9.2 percentage points.
  arXiv  Detail & Related papers  (2026-02-04T00:12:30Z)
• Impute-MACFM: Imputation based on Mask-Aware Flow Matching [1.9483189922830135]
  Impute-MACFM is a conditional flow matching framework for tabular imputation.<n>It addresses missingness mechanisms, missing completely at random, missing at random, and missing not at random.<n>It builds trajectories only on missing entries while constraining predicted velocity to remain near zero on observed entries.
  arXiv  Detail & Related papers  (2025-09-27T05:15:09Z)
• AIM: Amending Inherent Interpretability via Self-Supervised Masking [57.17600766859953]
  We propose "Amending Inherent Interpretability via Self-Supervised Masking" (AIM)<n>AIM promotes the network's utilization of genuine features over spurious alternatives without requiring additional annotations.<n>We validate AIM across a range of challenging datasets that test both out-of-distribution generalization and fine-grained visual understanding.
  arXiv  Detail & Related papers  (2025-08-15T14:29:59Z)
• DynaNoise: Dynamic Probabilistic Noise Injection for Defending Against Membership Inference Attacks [6.610581923321801]
  Membership Inference Attacks (MIAs) pose a significant risk to the privacy of training datasets.<n>Traditional mitigation techniques rely on injecting a fixed amount of noise during training or inference.<n>We present DynaNoise, an adaptive approach that dynamically modulates noise injection based on query sensitivity.
  arXiv  Detail & Related papers  (2025-05-19T17:07:00Z)
• ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation [91.20492150248106]
  We investigate the internal mechanisms behind unfaithful generation and identify a subset of mid-to-deep feed-forward networks (FFNs) that are disproportionately activated in such cases.<n>We propose Parametric Knowledge Muting through FFN Suppression (ParamMute), a framework that improves contextual faithfulness by suppressing the activation of unfaithfulness-associated FFNs.<n> Experimental results show that ParamMute significantly enhances faithfulness across both CoFaithfulQA and the established ConFiQA benchmark, achieving substantial reductions in reliance on parametric memory.
  arXiv  Detail & Related papers  (2025-02-21T15:50:41Z)
• dugMatting: Decomposed-Uncertainty-Guided Matting [83.71273621169404]
  We propose a decomposed-uncertainty-guided matting algorithm, which explores the explicitly decomposed uncertainties to efficiently and effectively improve the results. The proposed matting framework relieves the requirement for users to determine the interaction areas by using simple and efficient labeling.
  arXiv  Detail & Related papers  (2023-06-02T11:19:50Z)
• RARE: Robust Masked Graph Autoencoder [45.485891794905946]
  Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm. We propose a novel SGP method termed Robust mAsked gRaph autoEncoder (RARE) to improve the certainty in inferring masked data.
  arXiv  Detail & Related papers  (2023-04-04T03:35:29Z)
• Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis [61.68061613161187]
  Z-Mask is a robust and effective strategy to improve the robustness of convolutional networks against adversarial attacks. The presented defense relies on specific Z-score analysis performed on the internal network features to detect and mask the pixels corresponding to adversarial objects in the input image. Additional experiments showed that Z-Mask is also robust against possible defense-aware attacks.
  arXiv  Detail & Related papers  (2022-03-14T17:41:46Z)
• Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning [54.15303628138665]
  Face anti-spoofing (FAS) plays a vital role in preventing face recognition systems from presentation attacks. Existing face anti-spoofing datasets lack diversity due to the insufficient identity and insignificant variance. We propose Dual Spoof Disentanglement Generation framework to tackle this challenge by "anti-spoofing via generation"
  arXiv  Detail & Related papers  (2021-12-01T15:36:59Z)
• Reliable Probabilistic Face Embeddings in the Wild [5.094757968178221]
  Probabilistic Face Embeddings (PFE) can improve face recognition performance in unconstrained scenarios. PFE methods tend to be over-confident in estimating uncertainty and is too slow to apply to large-scale face matching. This paper proposes a regularized probabilistic face embedding method to improve the robustness and speed of PFE.
  arXiv  Detail & Related papers  (2021-02-08T09:27:57Z)

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.