Adaptive Causal Alignment for High-Confidence Adversarial Training

• URL: http://arxiv.org/abs/2606.03925v1
• Date: Tue, 02 Jun 2026 17:14:54 GMT
• Title: Adaptive Causal Alignment for High-Confidence Adversarial Training
• Abstract summary: Inverse adversarial training leverages high-confidence predictions to stabilize robust learning.<n>We propose High-Confidence Causally Aligned Training (HICAT), a unified framework that establishes a Semantic Equilibrium.
• Score: 32.04694519643468
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inverse adversarial training leverages high-confidence predictions to stabilize robust learning, yet we uncover a critical paradox: high confidence often stems from overfitting to non-causal background correlations rather than intrinsic object semantics. Our investigation reveals that visual context functions as a dual-natured signal, serving as either a necessary supportive prior or a spurious confounder. This insight renders existing blind suppression strategies flawed, as they inevitably lead to severe Feature Loss. To resolve this, we propose High-Confidence Causally Aligned Training (HICAT), a unified framework that establishes a Semantic Equilibrium. Operating on a ``Measure-Debias-Align'' pipeline, HICAT integrates a Learnable Background-Bias Estimator (LBBE) to adaptively diagnose context utility. Guided by this diagnosis, an Adaptive Debiasing mechanism performs surgical logit rectification, complemented by a geometrically grounded Foreground Logit Orthogonal Enhancement (FLOE) loss to enforce rigorous feature disentanglement. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-1K demonstrate that HICAT consistently improves over matched baselines across diverse architectures (CNNs and ViTs) while significantly reducing the robust generalization gap.

Related papers

• ProCA: Progressive Contrastive Alignment for Robust EEG Visual Decoding [47.35612571473169]
  EEG visual decoding aims to recover visual semantics from non-invasive neural time-series signals.<n>Existing methods rely on fixed visual or textual anchors whose semantic relations may become misaligned with EEG representations that vary across trials, subjects, and learning stages.<n>We propose Progressive Contrastive Alignment (ProCA), a unified and model-agnostic framework for adaptive neural-semantic alignment.
  arXiv  Detail & Related papers  (2026-09-04T12:48:25Z)
• Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition [5.310289270050359]
  Dynamic-Adaptive Contrastive Learning (DyCo-CL) is a geometry-aware framework that couples Virtual Adrialversa Augmentation (VAA) with a semantic consistency loss.<n>DyCo-CL achieves a 6.27% accuracy gain in 1-shot settings over prior methods.
  arXiv  Detail & Related papers  (2026-05-26T06:33:57Z)
• PDCR: Perception-Decomposed Confidence Reward for Vision-Language Reasoning [80.94559742826083]
  Reinforcement Learning with Verifiable Rewards (RLVR) traditionally relies on a sparse, outcome-based signal.<n>Recent work shows that providing a fine-grained, model-intrinsic signal effectively improves language reasoning training by providing step-level guidance without costly external models.<n>While effective for unimodal text, we find that naively applying this global reward to vision-language (V-L) reasoning is a suboptimal strategy.<n>We propose Perception-Decomposed Confidence Reward (PDCR), a framework that solves this by aligning the reward structure with the task's heterogeneous nature.
  arXiv  Detail & Related papers  (2026-05-13T12:55:18Z)
• Multimodal Learning on Low-Quality Data with Conformal Predictive Self-Calibration [72.0672328514289]
  Multimodal learning often grapples with the challenge of low-quality data.<n>We propose a unified framework, termed Conformal Predictive Self-Calibration.<n>Our framework consistently outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-05T14:48:52Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• Less Approximates More: Harmonizing Performance and Confidence Faithfulness via Hybrid Post-Training for High-Stakes Tasks [52.81286869496811]
  Large language models are increasingly deployed in high-stakes tasks, where confident yet incorrect inferences may cause real-world harm.<n>We propose to jointly optimize unsupervised Reinforcement Learning from Internal Feedback with reasoning-trace-guided Reasoning Distillation.<n>We introduce HyTuning, a hybrid post-training framework that adaptively reweights RD and RLIF via a PRG-style metric.
  arXiv  Detail & Related papers  (2026-04-09T16:50:11Z)
• Explainability-Guided Defense: Attribution-Aware Model Refinement Against Adversarial Data Attacks [6.573058520271728]
  We identify a connection between interpretability and robustness that can be directly leveraged during training.<n>We introduce an attribution-guided refinement framework that transforms Local Interpretable Model-Agnostic Explanations into an active training signal.
  arXiv  Detail & Related papers  (2026-01-02T19:36:03Z)
• OptiGradTrust: Byzantine-Robust Federated Learning with Multi-Feature Gradient Analysis and Reinforcement Learning-Based Trust Weighting [3.112384742740621]
  Federated Learning (FL) enables collaborative model training across distributed medical institutions while preserving patient privacy.<n>We present OptiGradTrust, a comprehensive defense framework that evaluates updates through a novel six-dimensional fingerprint.<n>We develop FedBN-ProxFedBN-P, combining Federated Batch Normalization with regularization for optimal accuracy-convergence trade-offs.
  arXiv  Detail & Related papers  (2025-07-31T15:14:36Z)
• Source-Free Domain Adaptive Object Detection with Semantics Compensation [54.00183496587841]
  We introduce Weak-to-strong Semantics Compensation (WSCo) for strong data augmentation.<n>WSCo compensates for the class-relevant semantics that may be lost during strong augmentation on the fly.<n>WSCo can be implemented as a generic plug-in, easily integrable with any existing SFOD pipelines.
  arXiv  Detail & Related papers  (2024-10-07T23:32:06Z)
• Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment [24.577363665112706]
  Under inverse adversarial attacks, high-confidence outputs are influenced by biased feature activations.<n>This spurious correlation bias leads to overfitting irrelevant background features during adversarial training.<n>We propose Debiased High-Confidence Adversarial Training (DHAT), a novel approach that aligns adversarial logits with debiased high-confidence logits.
  arXiv  Detail & Related papers  (2024-08-12T11:56:06Z)

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.